papers

Publications (363)

cs.CL2020

Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network

Shuqing Bian, Xu Chen, Wayne Xin Zhao +5

With the ever-increasing growth of online recruitment data, job-resume matching has become an important task to automatically match jobs with suitable resumes. This task is typical…

cs.IR2025

Tapping the Potential of Large Language Models as Recommender Systems: A Comprehensive Framework and Empirical Analysis

Lanling Xu, Junjie Zhang, Bingqian Li +4

Recently, Large Language Models~(LLMs) such as ChatGPT have showcased remarkable abilities in solving general tasks, demonstrating the potential for applications in recommender sys…

cs.AI2024

Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training

Jinxia Yang, Bing Su, Wayne Xin Zhao +1

Medical vision-language pre-training methods mainly leverage the correspondence between paired medical images and radiological reports. Although multi-view spatial images and tempo…

cs.IR2025

Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation

Bowen Zheng, Zihan Lin, Enze Liu +5

Nowadays, reading or writing comments on captivating videos has emerged as a critical part of the viewing experience on online video platforms. However, existing recommender system…

cs.DB2013

Mining Frequent Neighborhood Patterns in Large Labeled Graphs

Jialong Han, Ji-Rong Wen

Over the years, frequent subgraphs have been an important sort of targeted patterns in the pattern mining literatures, where most works deal with databases holding a number of grap…

cs.IR2026

Learning to Retrieve from Agent Trajectories

Yuqi Zhou, Sunhao Dai, Changle Qu +3

Information retrieval (IR) systems have traditionally been designed and trained for human users, with learning-to-rank methods relying heavily on large-scale human interaction logs…

cs.IR2026

DiffuRank: Effective Document Reranking with Diffusion Language Models

Qi Liu, Kun Ai, Jiaxin Mao +6

Recent advances in large language models (LLMs) have inspired new paradigms for document reranking. While this paradigm better exploits the reasoning and contextual understanding c…

cs.CL2024

Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models

Jie Chen, Yupeng Zhang, Bingning Wang +3

Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs). Studies have shown that synthetic…

cs.IR2024

EulerFormer: Sequential User Behavior Modeling with Complex Vector Attention

Zhen Tian, Wayne Xin Zhao, Changwang Zhang +3

To capture user preference, transformer models have been widely applied to model sequential user behavior data. The core of transformer architecture lies in the self-attention mech…

cs.CL2023

Improving Conversational Recommendation Systems via Counterfactual Data Simulation

Xiaolei Wang, Kun Zhou, Xinyu Tang +4

Conversational recommender systems (CRSs) aim to provide recommendation services via natural language conversations. Although a number of approaches have been proposed for developi…

cs.CV2025

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Yifan Li, Hangyu Guo, Kun Zhou +2

In this paper, we study the harmlessness alignment problem of multimodal large language models (MLLMs). We conduct a systematic empirical analysis of the harmlessness performance o…

cs.MA2025

Benchmarking LLMs' Swarm intelligence

Kai Ruan, Mowen Huang, Ji-Rong Wen +1

Large Language Models (LLMs) show potential for complex reasoning, yet their capacity for emergent coordination in Multi-Agent Systems (MAS) when operating under strict swarm-like…

cs.CL2021

Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models

Junyi Li, Tianyi Tang, Wayne Xin Zhao +3

This paper studies how to automatically generate a natural language text that describes the facts in knowledge graph (KG). Considering the few-shot setting, we leverage the excelle…

cs.CL2025

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

Changle Qu, Sunhao Dai, Xiaochi Wei +5

Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent i…

cs.IR2026

ClawRec: A Claw-Native Recommender System

Chenghao Wu, Kesha Ou, Xiaolei Wang +8

Recommender systems have become integral to navigating the modern digital ecosystem. Yet most deployed systems remain confined within single-platform boundaries, observing localize…

cs.CL2026

WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search

Xiaoshuai Song, Liancheng Zhang, Kangzhi Zhao +8

Large language model (LLM)-based web search agents are transforming information seeking from simple factoid question answering into complex, deep-and-wide search and research-orien…

cs.CL2024

Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs

Jiejun Tan, Zhicheng Dou, Yutao Zhu +3

The integration of large language models (LLMs) and search engines represents a significant evolution in knowledge acquisition methodologies. However, determining the knowledge tha…

cs.CL2026

Computer Environments Elicit General Agentic Intelligence in LLMs

Daixuan Cheng, Shaohan Huang, Yuxian Gu +6

Agentic intelligence in large language models (LLMs) requires not only model intrinsic capabilities but also interactions with external environments. Equipping LLMs with computers…

cs.CL2024

YuLan: An Open-source Large Language Model

Yutao Zhu, Kun Zhou, Kelong Mao +35

Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many o…

cs.DS2024

Approximating Single-Source Personalized PageRank with Absolute Error Guarantees

Zhewei Wei, Ji-Rong Wen, Mingji Yang

Personalized PageRank (PPR) is an extensively studied and applied node proximity measure in graphs. For a pair of nodes and on a graph , the PPR value is…

cs.CV2022

Learning to Answer Questions in Dynamic Audio-Visual Scenarios

Guangyao Li, Yake Wei, Yapeng Tian +3

In this paper, we focus on the Audio-Visual Question Answering (AVQA) task, which aims to answer questions regarding different visual objects, sounds, and their associations in vid…

cs.CL2020

Knowledge-Enhanced Personalized Review Generation with Capsule Graph Neural Network

Junyi Li, Siqing Li, Wayne Xin Zhao +4

Personalized review generation (PRG) aims to automatically produce review text reflecting user preference, which is a challenging natural language generation task. Most of previous…

cs.CL2024

Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector

Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao +5

Hallucination detection is a challenging task for large language models (LLMs), and existing studies heavily rely on powerful closed-source LLMs such as GPT-4. In this paper, we pr…

cs.IR2022

Towards Universal Sequence Representation Learning for Recommender Systems

Yupeng Hou, Shanlei Mu, Wayne Xin Zhao +3

In order to develop effective sequential recommenders, a series of sequence representation learning (SRL) methods are proposed to model historical user behaviors. Most existing SRL…

cs.CL2021

Knowledge-based Review Generation by Coherence Enhanced Text Planning

Junyi Li, Wayne Xin Zhao, Zhicheng Wei +2

As a natural language generation task, it is challenging to generate informative and coherent review text. In order to enhance the informativeness of the generated text, existing s…

cs.CL2024

ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting

Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao +1

Chain-of-Thought (CoT) prompting can enhance the reasoning capabilities of large language models (LLMs), establishing itself as a primary approach to solving complex reasoning task…

cs.IR2023

RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit

Jiongnan Liu, Jiajie Jin, Zihan Wang +3

Although Large Language Models (LLMs) have demonstrated extraordinary capabilities in many domains, they still have a tendency to hallucinate and generate fictitious responses to u…

cs.IR2023

Law Article-Enhanced Legal Case Matching: a Causal Learning Approach

Zhongxiang Sun, Jun Xu, Xiao Zhang +2

Legal case matching, which automatically constructs a model to estimate the similarities between the source and target cases, has played an essential role in intelligent legal syst…

cs.IR2023

AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems

Junjie Zhang, Yupeng Hou, Ruobing Xie +5

Recently, there has been an emergence of employing LLM-powered agents as believable human proxies, based on their remarkable decision-making capability. However, existing studies m…

cs.CL2021

Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding

Junyi Li, Wayne Xin Zhao, Ji-Rong Wen +1

Generating long and informative review text is a challenging natural language generation task. Previous work focuses on word-level generation, neglecting the importance of topical…

cs.CL2024

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models

Changyu Chen, Xiting Wang, Ting-En Lin +6

In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approach…

cs.LG2024

Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited

Mingguo He, Zhewei Wei, Ji-Rong Wen

Designing spectral convolutional networks is a challenging problem in graph learning. ChebNet, one of the early attempts, approximates the spectral graph convolutions using Chebysh…

cs.LG2020

Few-Shot Learning as Domain Adaptation: Algorithm and Analysis

Jiechao Guan, Zhiwu Lu, Tao Xiang +1

To recognize the unseen classes with only few samples, few-shot learning (FSL) uses prior knowledge learned from the seen classes. A major challenge for FSL is that the distributio…

cs.IR2020

S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization

Kun Zhou, Hui Wang, Wayne Xin Zhao +5

Recently, significant progress has been made in sequential recommendation with deep learning. Existing neural sequential recommendation models usually rely on the item prediction l…

cs.CL2025

Improving Retrospective Language Agents via Joint Policy Gradient Optimization

Xueyang Feng, Bo Lan, Quanyu Dai +5

In recent research advancements within the community, large language models (LLMs) have sparked great interest in creating autonomous agents. However, current prompt-based agents o…

cs.IR2024

CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation

Yiruo Cheng, Kelong Mao, Ziliang Zhao +6

Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attentio…

cs.AI2025

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework

Jie Chen, Jinhao Jiang, Yingqian Min +4

Large reasoning models (LRMs) have exhibited strong performance on complex reasoning tasks, with further gains achievable through increased computational budgets at inference. Howe…

cs.CL2026

Toward Autonomous Long-Horizon Engineering for ML Research

Guoxin Chen, Jie Chen, Lei Chen +7

Agentic systems increasingly automate pieces of AI research. Yet turning underspecified research objectives into runnable, experimentally validated ML systems remains a central bot…

cs.CL2024

Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint

Zhipeng Chen, Kun Zhou, Wayne Xin Zhao +4

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing R…

cs.LG2024

Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning

Xiaolei Wang, Xinyu Tang, Wayne Xin Zhao +1

The emergence of in-context learning (ICL) is potentially attributed to two major abilities: task recognition (TR) for recognizing the task from demonstrations and utilizing pre-tr…

cs.CV2024

Self-supervised Audiovisual Representation Learning for Remote Sensing Data

Konrad Heidler, Lichao Mou, Di Hu +5

Many current deep learning approaches make extensive use of backbone networks pre-trained on large datasets like ImageNet, which are then fine-tuned to perform a certain task. In r…

cs.CL2023

UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph

Jinhao Jiang, Kun Zhou, Wayne Xin Zhao +1

Multi-hop Question Answering over Knowledge Graph~(KGQA) aims to find the answer entities that are multiple hops away from the topic entities mentioned in a natural language questi…

cs.IR2024

Selecting Query-bag as Pseudo Relevance Feedback for Information-seeking Conversations

Xiaoqing Zhang, Xiuying Chen, Shen Gao +4

Information-seeking dialogue systems are widely used in e-commerce systems, with answers that must be tailored to fit the specific settings of the online system. Given the user que…

cs.CL2026

Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models

Haoxiang Sun, Yingqian Min, Zhipeng Chen +2

The rapid advancement of large reasoning models has saturated existing math benchmarks, underscoring the urgent need for more challenging evaluation frameworks. To address this, we…

cs.IR2025

Test-Time Alignment for Tracking User Interest Shifts in Sequential Recommendation

Changshuo Zhang, Xiao Zhang, Teng Shi +2

Sequential recommendation is essential in modern recommender systems, aiming to predict the next item a user may interact with based on their historical behaviors. However, real-wo…

cs.AI2026

LLM Agents as Social Scientists: A Human-AI Collaborative Platform for Social Science Automation

Lei Wang, Yuanzi Li, Jinchao Wu +4

Traditional social science research often requires designing complex experiments across vast methodological spaces and depends on real human participants, making it labor-intensive…

cs.LG2021

Scalable Graph Neural Networks via Bidirectional Propagation

Ming Chen, Zhewei Wei, Bolin Ding +4

Graph Neural Networks (GNN) is an emerging field for learning on non-Euclidean data. Recently, there has been increased interest in designing GNN that scales to large graphs. Most…

cs.IR2025

Pre-training Generative Recommender with Multi-Identifier Item Tokenization

Bowen Zheng, Enze Liu, Zhongfu Chen +4

Generative recommendation autoregressively generates item identifiers to recommend potential items. Existing methods typically adopt a one-to-one mapping strategy, where each item…

cs.CL2023

ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph

Jinhao Jiang, Kun Zhou, Wayne Xin Zhao +2

Question Answering over Knowledge Graph (KGQA) aims to seek answer entities for the natural language question from a large-scale Knowledge Graph~(KG). To better perform reasoning o…

cs.CL2021

Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals

Gaole He, Yunshi Lan, Jing Jiang +2

Multi-hop Knowledge Base Question Answering (KBQA) aims to find the answer entities that are multiple hops away in the Knowledge Base (KB) from the entities in the question. A majo…

cs.CV2024

Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing

Wenyi Mo, Tianyu Zhang, Yalong Bai +2

Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to p…

cs.IR2023

Alleviating the Long-Tail Problem in Conversational Recommender Systems

Zhipeng Zhao, Kun Zhou, Xiaolei Wang +4

Conversational recommender systems (CRS) aim to provide the recommendation service via natural language conversations. To develop an effective CRS, high-quality CRS datasets are ve…

cs.CL2026

ClawGym: A Scalable Framework for Building Effective Claw Agents

Fei Bai, Huatong Song, Shuang Sun +11

Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains const…

cs.CL2025

ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests

Shiyi Xu, Yiwen Hu, Yingqian Min +3

With the significant progress of large reasoning models in complex coding and reasoning tasks, existing benchmarks, like LiveCodeBench and CodeElo, are insufficient to evaluate the…

cs.MA2024

Very Large-Scale Multi-Agent Simulation in AgentScope

Xuchen Pan, Dawei Gao, Yuexiang Xie +6

Recent advances in large language models (LLMs) have opened new avenues for applying multi-agent systems in very large-scale simulations. However, there remain several challenges w…

cs.CL2024

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models

Ang Lv, Yuhan Chen, Kaiyi Zhang +5

In this paper, we delve into several mechanisms employed by Transformer-based language models (LLMs) for factual recall tasks. We outline a pipeline consisting of three major steps…

cs.CL2021

CRSLab: An Open-Source Toolkit for Building Conversational Recommender System

Kun Zhou, Xiaolei Wang, Yuanhang Zhou +5

In recent years, conversational recommender system (CRS) has received much attention in the research community. However, existing studies on CRS vary in scenarios, goals and techni…

cs.CV2024

On-the-fly Modulation for Balanced Multimodal Learning

Yake Wei, Di Hu, Henghui Du +1

Multimodal learning is expected to boost model performance by integrating information from different modalities. However, its potential is not fully exploited because the widely-us…

cs.CV2018

Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation

Yulei Niu, Zhiwu Lu, Ji-Rong Wen +2

Image annotation aims to annotate a given image with a variable number of class labels corresponding to diverse visual concepts. In this paper, we address two main issues in large-…

cs.IR2022

Feature-aware Diversified Re-ranking with Disentangled Representations for Relevant Recommendation

Zihan Lin, Hui Wang, Jingshu Mao +4

Relevant recommendation is a special recommendation scenario which provides relevant items when users express interests on one target item (e.g., click, like and purchase). Besides…

cs.AI2026

OmniGAIA: Towards Native Omni-Modal AI Agents

Xiaoxi Li, Wenxiang Jiao, Jiarui Jin +10

Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world. However,…

cs.CL2024

ICLEval: Evaluating In-Context Learning Ability of Large Language Models

Wentong Chen, Yankai Lin, ZhenHao Zhou +4

In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs. Evaluating the ICL abi…

cs.IR2022

Leveraging Search History for Improving Person-Job Fit

Yupeng Hou, Xingyu Pan, Wayne Xin Zhao +4

As the core technique of online recruitment platforms, person-job fit can improve hiring efficiency by accurately matching job positions with qualified candidates. However, existin…

cs.IR2015

A General SIMD-based Approach to Accelerating Compression Algorithms

Wayne Xin Zhao, Xudong Zhang, Daniel Lemire +4

Compression algorithms are important for data oriented tasks, especially in the era of Big Data. Modern processors equipped with powerful SIMD instruction sets, provide us an oppor…

cs.IR2024

Enhancing Graph Contrastive Learning with Reliable and Informative Augmentation for Recommendation

Bowen Zheng, Junjie Zhang, Hongyu Lu +4

Graph neural network(GNN) has been a powerful approach in collaborative filtering(CF) due to its ability to model high-order user-item relationships. Recently, to alleviate the dat…

cs.CL2025

KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing

Rui Li, Quanyu Dai, Zeyu Zhang +3

Recent advances in retrieval-augmented generation (RAG) furnish large language models (LLMs) with iterative retrievals of relevant information to handle complex multi-hop questions…

cs.CL2024

Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment

Jinhao Jiang, Junyi Li, Wayne Xin Zhao +3

Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-tr…

cs.IR2022

CDSM: Cascaded Deep Semantic Matching on Textual Graphs Leveraging Ad-hoc Neighbor Selection

Jing Yao, Zheng Liu, Junhan Yang +3

Deep semantic matching aims to discriminate the relationship between documents based on deep neural networks. In recent years, it becomes increasingly popular to organize documents…

cs.LG2021

Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators

Peiyu Liu, Ze-Feng Gao, Wayne Xin Zhao +3

This paper presents a novel pre-trained language models (PLM) compression approach based on the matrix product operator (short as MPO) from quantum many-body physics. It can decomp…

cs.IR2025

Addressing Personalized Bias for Unbiased Learning to Rank

Zechun Niu, Lang Mei, Liu Yang +4

Unbiased learning to rank (ULTR), which aims to learn unbiased ranking models from biased user behavior logs, plays an important role in Web search. Previous research on ULTR has s…

cs.CV2018

Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning

Aoxue Li, Zhiwu Lu, Jiechao Guan +3

Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to unseen ones so that the latter can be recognised without any training samples. This is made possible by lea…

cs.IR2023

EulerNet: Adaptive Feature Interaction Learning via Euler's Formula for CTR Prediction

Zhen Tian, Ting Bai, Wayne Xin Zhao +2

Learning effective high-order feature interactions is very crucial in the CTR prediction task. However, it is very time-consuming to calculate high-order feature interactions with…

cs.IR2022

Negative Sampling for Contrastive Representation Learning: A Review

Lanling Xu, Jianxun Lian, Wayne Xin Zhao +5

The learn-to-compare paradigm of contrastive representation learning (CRL), which compares positive samples with negative ones for representation learning, has achieved great succe…

cs.CV2026

Towards Long-horizon Agentic Multimodal Search

Yifan Du, Zikang Liu, Jinbiao Peng +5

Multimodal deep search agents have shown great potential in solving complex tasks by iteratively collecting textual and visual evidence. However, managing the heterogeneous informa…

cs.IR2025

Modeling Domain and Feedback Transitions for Cross-Domain Sequential Recommendation

Changshuo Zhang, Teng Shi, Xiao Zhang +4

Nowadays, many recommender systems encompass various domains to cater to users' diverse needs, leading to user behaviors transitioning across different domains. In fact, user behav…

cs.IR2022

Enhancing User Behavior Sequence Modeling by Generative Tasks for Session Search

Haonan Chen, Zhicheng Dou, Yutao Zhu +3

Users' search tasks have become increasingly complicated, requiring multiple queries and interactions with the results. Recent studies have demonstrated that modeling the historica…

cs.IR2025

HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

Jiejun Tan, Zhicheng Dou, Yan Yu +4

Recently, large reasoning models have demonstrated strong mathematical and coding abilities, and deep search leverages their reasoning capabilities in challenging information retri…

cs.LG2022

Privacy-Preserved Neural Graph Similarity Learning

Yupeng Hou, Wayne Xin Zhao, Yaliang Li +1

To develop effective and efficient graph similarity learning (GSL) models, a series of data-driven neural algorithms have been proposed in recent years. Although GSL models are fre…

cs.IR2024

QAGCF: Graph Collaborative Filtering for Q&A Recommendation

Changshuo Zhang, Teng Shi, Xiao Zhang +5

Question and answer (Q&A) platforms usually recommend question-answer pairs to meet users' knowledge acquisition needs, unlike traditional recommendations that recommend only one i…

cs.IR2026

ChatShopBuddy: Towards Reliable Conversational Shopping Agents via Reinforcement Learning

Yiruo Cheng, Kelong Mao, Tianhao Li +3

Conversational shopping agents represent a critical consumer-facing application of Large Language Model (LLM)-powered agents, yet how to effectively apply post-training Reinforceme…

cs.AI2024

MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants

Zeyu Zhang, Quanyu Dai, Luyu Chen +7

LLM-based agents have been widely applied as personal assistants, capable of memorizing information from user messages and responding to personal queries. However, there still lack…

cs.CL2023

JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving

Wayne Xin Zhao, Kun Zhou, Beichen Zhang +8

Although pre-trained language models~(PLMs) have recently advanced the research progress in mathematical reasoning, they are not specially designed as a capable multi-task solver,…

cs.CL2023

MVP: Multi-task Supervised Pre-training for Natural Language Generation

Tianyi Tang, Junyi Li, Wayne Xin Zhao +1

Pre-trained language models (PLMs) have achieved remarkable success in natural language generation (NLG) tasks. Up to now, most NLG-oriented PLMs are pre-trained in an unsupervised…

cs.IR2021

USER: A Unified Information Search and Recommendation Model based on Integrated Behavior Sequence

Jing Yao, Zhicheng Dou, Ruobing Xie +3

Search and recommendation are the two most common approaches used by people to obtain information. They share the same goal -- satisfying the user's information need at the right t…

cs.CL2026

Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences

Mingyang Li, Yurou Liu, Jieping Ye +3

In this report, we present LOGOS (Language Of Generative Objects in Science), a scientific generative language model that unifies heterogeneous tasks across the natural sciences wi…

cs.CL2025

Towards Effective Code-Integrated Reasoning

Fei Bai, Yingqian Min, Beichen Zhang +6

In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire thi…

cs.CL2025

FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research

Jiajie Jin, Yutao Zhu, Guanting Dong +7

With the advent of large language models (LLMs) and multimodal large language models (MLLMs), the potential of retrieval-augmented generation (RAG) has attracted considerable resea…

cs.IR2021

PSSL: Self-supervised Learning for Personalized Search with Contrastive Sampling

Yujia Zhou, Zhicheng Dou, Yutao Zhu +1

Personalized search plays a crucial role in improving user search experience owing to its ability to build user profiles based on historical behaviors. Previous studies have made g…

cs.AI2024

Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems

Yingqian Min, Zhipeng Chen, Jinhao Jiang +11

Recently, slow-thinking reasoning systems, such as o1, have demonstrated remarkable capabilities in solving complex reasoning tasks. These systems typically engage in an extended t…

cs.CV2023

Zero-shot Visual Question Answering with Language Model Feedback

Yifan Du, Junyi Li, Tianyi Tang +2

In this paper, we propose a novel language model guided captioning approach, LAMOC, for knowledge-based visual question answering (VQA). Our approach employs the generated captions…

cs.CL2022

SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval

Kun Zhou, Yeyun Gong, Xiao Liu +8

Sampling proper negatives from a large document pool is vital to effectively train a dense retrieval model. However, existing negative sampling strategies suffer from the uninforma…

cs.CL2022

Context-Tuning: Learning Contextualized Prompts for Natural Language Generation

Tianyi Tang, Junyi Li, Wayne Xin Zhao +1

Recently, pretrained language models (PLMs) have had exceptional success in language generation. To leverage the rich knowledge encoded by PLMs, a simple yet powerful paradigm is t…

cs.CL2024

Large Language Model-based Human-Agent Collaboration for Complex Task Solving

Xueyang Feng, Zhi-Yuan Chen, Yujia Qin +4

In recent developments within the research community, the integration of Large Language Models (LLMs) in creating fully autonomous agents has garnered significant interest. Despite…

cs.CL2025

Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models

Zhipeng Chen, Kun Zhou, Liang Song +4

Multi-lingual ability transfer has become increasingly important for the broad application of large language models (LLMs). Existing work highly relies on training with the multi-l…

cs.AI2024

DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy

Hongda Sun, Weikai Xu, Wei Liu +5

Recent advances in large language models (LLMs) have revolutionized the landscape of reasoning tasks. To enhance the capabilities of LLMs to emulate human reasoning, prior studies…

cs.CL2025

Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers

Xinyu Tang, Xiaolei Wang, Wayne Xin Zhao +3

Automatic prompt optimization is an important approach to improving the performance of large language models (LLMs). Recent research demonstrates the potential of using LLMs as pro…

cs.IR2022

Filter-enhanced MLP is All You Need for Sequential Recommendation

Kun Zhou, Hui Yu, Wayne Xin Zhao +1

Recently, deep neural networks such as RNN, CNN and Transformer have been applied in the task of sequential recommendation, which aims to capture the dynamic preference characteris…

cs.IR2022

Measuring "Why" in Recommender Systems: a Comprehensive Survey on the Evaluation of Explainable Recommendation

Xu Chen, Yongfeng Zhang, Ji-Rong Wen

Explainable recommendation has shown its great advantages for improving recommendation persuasiveness, user satisfaction, system transparency, among others. A fundamental problem o…

cs.IR2024

LTP-MMF: Towards Long-term Provider Max-min Fairness Under Recommendation Feedback Loops

Chen Xu, Xiaopeng Ye, Jun Xu +3

Multi-stakeholder recommender systems involve various roles, such as users, and providers. Previous work pointed out that max-min fairness (MMF) is a better metric to support weak…

cs.LG2026

Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductor Discovery

Mingze Li, Yu Rong, Songyou Li +16

Artificial intelligence has accelerated materials discovery through high-throughput prediction and generation, yet the decision problem remains a formidable bottleneck. While curre…