Publications (132)
Exploring Lottery Prompts for Pre-trained Language Models
Yulin Chen, Ning Ding, Xiaobin Wang +4
Consistently scaling pre-trained language models (PLMs) imposes substantial burdens on model adaptation, necessitating more efficient alternatives to conventional fine-tuning. Give…
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…
WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking
Zhengwei Tao, Haiyang Shen, Baixuan Li +11
Large Language Model (LLM)-based agents have emerged as a transformative approach for open-ended problem solving, with information seeking (IS) being a core capability that enables…
Editing Personality for Large Language Models
Shengyu Mao, Xiaohan Wang, Mengru Wang +4
This paper introduces an innovative task focused on editing the personality traits of Large Language Models (LLMs). This task seeks to adjust the models' responses to opinion-relat…
Geo-Encoder: A Chunk-Argument Bi-Encoder Framework for Chinese Geographic Re-Ranking
Yong Cao, Ruixue Ding, Boli Chen +5
Chinese geographic re-ranking task aims to find the most relevant addresses among retrieved candidates, which is crucial for location-related services such as navigation maps. Unli…
DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition
Zeqi Tan, Shen Huang, Zixia Jia +8
The MultiCoNER \RNum{2} shared task aims to tackle multilingual named entity recognition (NER) in fine-grained and noisy scenarios, and it inherits the semantic ambiguity and low-c…
Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting
Linzhi Wu, Pengjun Xie, Jie Zhou +4
Self-augmentation has received increasing research interest recently to improve named entity recognition (NER) performance in low-resource scenarios. Token substitution and mixup a…
Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts
Zhuo Chen, Xinyu Wang, Yong Jiang +3
In the era of large language models, applying techniques such as Retrieval Augmented Generation can better address Open-Domain Question-Answering problems. Due to constraints inclu…
EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce
Rui Min, Zile Qiao, Ze Xu +18
Foundation agents have rapidly advanced in their ability to reason and interact with real environments, making the evaluation of their core capabilities increasingly important. Whi…
Towards General Text Embeddings with Multi-stage Contrastive Learning
Zehan Li, Xin Zhang, Yanzhao Zhang +3
We present GTE, a general-purpose text embedding model trained with multi-stage contrastive learning. In line with recent advancements in unifying various NLP tasks into a single f…
Tongyi DeepResearch Technical Report
Tongyi DeepResearch Team, Baixuan Li, Bo Zhang +54
We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous…
Scaling Generalist Data-Analytic Agents
Shuofei Qiao, Yanqiu Zhao, Zhisong Qiu +8
Data-analytic agents are emerging as a key catalyst for automated scientific discovery and for the vision of Innovating AI. Current approaches, however, rely heavily on prompt engi…
ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking
Baixuan Li, Dingchu Zhang, Jialong Wu +9
Parallel thinking expands exploration breadth, complementing the deep exploration of information-seeking (IS) agents to further enhance problem-solving capability. However, convent…
BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents
Litu Ou, Kuan Li, Huifeng Yin +8
Confidence in LLMs is a useful indicator of model uncertainty and answer reliability. Existing work mainly focused on single-turn scenarios, while research on confidence in complex…
An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation
Peiming Guo, Sinuo Liu, Yanzhao Zhang +4
Photo-Sharing Multi-modal dialogue generation requires a dialogue agent not only to generate text responses but also to share photos at the proper moment. Using image text caption…
DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling
Hao Sun, Zile Qiao, Bo Wang +6
Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs) through the dynamic integration of external knowledge.…
Scaling Agents via Continual Pre-training
Liangcai Su, Zhen Zhang, Guangyu Li +19
Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approache…
Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenario
Feiteng Mu, Yong Jiang, Liwen Zhang +4
Current research on tool learning primarily focuses on selecting the most effective tool from a wide array of options, often overlooking cost-effectiveness, a crucial factor in hum…
U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents
Jin Su, Runnan Fang, Yeqiu Li +5
Large language model (LLM)-based agents have been successfully deployed in many tool-augmented settings, but their scalability is fundamentally constrained by context length. Exist…
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
Qiang Zhang, Boli Chen, Fanrui Zhang +14
Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast soluti…
UEmbed: Unified Sparse and Dense Multimodal Embeddings
Tingyu Song, Mingxin Li, Yanzhao Zhang +5
Sparse retrieval underpins modern search systems, from web search to retrieval-augmented generation. Existing work has introduced Learned Sparse Retrieval (LSR) to push beyond exac…
Efficient Multimodal Planning Agent for Visual Question-Answering
Zhuo Chen, Xinyu Geng, Xinyu Wang +4
Visual Question-Answering (VQA) is a challenging multimodal task that requires integrating visual and textual information to generate accurate responses. While multimodal Retrieval…
Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling
Peijie Jiang, Dingkun Long, Yanzhao Zhang +3
Boundary information is critical for various Chinese language processing tasks, such as word segmentation, part-of-speech tagging, and named entity recognition. Previous studies us…
SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement
Runnan Fang, Xiaobin Wang, Yuan Liang +8
In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges…
EcomGPT-CT: Continual Pre-training of E-commerce Large Language Models with Semi-structured Data
Shirong Ma, Shen Huang, Shulin Huang +6
Large Language Models (LLMs) pre-trained on massive corpora have exhibited remarkable performance on various NLP tasks. However, applying these models to specific domains still pos…
SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization
Qi Zhang, Zhaopeng Feng, Xiaonan Shi +8
Agent skills, which consist of reusable strategies that guide agent reasoning and action, have shown strong potential for improving model capability at inference time. However, cur…
Retrieval Oriented Masking Pre-training Language Model for Dense Passage Retrieval
Dingkun Long, Yanzhao Zhang, Guangwei Xu +1
Pre-trained language model (PTM) has been shown to yield powerful text representations for dense passage retrieval task. The Masked Language Modeling (MLM) is a major sub-task of t…
Probing BERT in Hyperbolic Spaces
Boli Chen, Yao Fu, Guangwei Xu +4
Recently, a variety of probing tasks are proposed to discover linguistic properties learned in contextualized word embeddings. Many of these works implicitly assume these embedding…
WebWalker: Benchmarking LLMs in Web Traversal
Jialong Wu, Wenbiao Yin, Yong Jiang +8
Retrieval-augmented generation (RAG) demonstrates remarkable performance across tasks in open-domain question-answering. However, traditional search engines may retrieve shallow co…
CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity
Jintao Liu, Ruixue Ding, Linhao Zhang +2
Retrieval-Augmented Generation (RAG) aims to enhance large language models (LLMs) to generate more accurate and reliable answers with the help of the retrieved context from externa…
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
Zhaopeng Feng, Liangcai Su, Zhen Zhang +16
As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing cont…
EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerce
Yangning Li, Shirong Ma, Xiaobin Wang +6
Recently, instruction-following Large Language Models (LLMs) , represented by ChatGPT, have exhibited exceptional performance in general Natural Language Processing (NLP) tasks. Ho…
FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence
Xinyu Yan, Boyang Chen, Jiaming Zhang +12
Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to concrete real-world claims, creating new challenges for verifying visual e…
Repurposing Synthetic Data for Fine-grained Search Agent Supervision
Yida Zhao, Kuan Li, Xixi Wu +11
LLM-based search agents are increasingly trained on entity-centric synthetic data to solve complex, knowledge-intensive tasks. However, prevailing training methods like Group Relat…
WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents
Zile Qiao, Guoxin Chen, Xuanzhong Chen +13
Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we in…
AgentFold: Long-Horizon Web Agents with Proactive Context Management
Rui Ye, Zhongwang Zhang, Kuan Li +12
LLM-based web agents show immense promise for information seeking, yet their effectiveness on long-horizon tasks is hindered by a fundamental trade-off in context management. Preva…
mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval
Xin Zhang, Yanzhao Zhang, Dingkun Long +10
We present systematic efforts in building long-context multilingual text representation model (TRM) and reranker from scratch for text retrieval. We first introduce a text encoder…
Benchmarking Agentic Workflow Generation
Shuofei Qiao, Runnan Fang, Zhisong Qiu +6
Large Language Models (LLMs), with their exceptional ability to handle a wide range of tasks, have driven significant advancements in tackling reasoning and planning tasks, wherein…
Named Entity and Relation Extraction with Multi-Modal Retrieval
Xinyu Wang, Jiong Cai, Yong Jiang +3
Multi-modal named entity recognition (NER) and relation extraction (RE) aim to leverage relevant image information to improve the performance of NER and RE. Most existing efforts l…
Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking
Ziqi Dai, Xin Zhang, Mingxin Li +6
In information retrieval, training reranking models mainly focuses on two types of objectives: metric learning (e.g. contrastive loss to increase the predicted scores on relevant q…
Modeling Label Correlations for Ultra-Fine Entity Typing with Neural Pairwise Conditional Random Field
Chengyue Jiang, Yong Jiang, Weiqi Wu +2
Ultra-fine entity typing (UFET) aims to predict a wide range of type phrases that correctly describe the categories of a given entity mention in a sentence. Most recent works infer…
Nested Browser-Use Learning for Agentic Information Seeking
Baixuan Li, Jialong Wu, Wenbiao Yin +8
Information-seeking (IS) agents have achieved strong performance across a range of wide and deep search tasks, yet their tool use remains largely restricted to API-level snippet re…
A Two-Stage Adaptation of Large Language Models for Text Ranking
Longhui Zhang, Yanzhao Zhang, Dingkun Long +3
Text ranking is a critical task in information retrieval. Recent advances in pre-trained language models (PLMs), especially large language models (LLMs), present new opportunities…
LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing
Kuan Li, Liwen Zhang, Yong Jiang +4
Effectively incorporating external knowledge into Large Language Models (LLMs) is crucial for enhancing their capabilities and addressing real-world needs. Retrieval-Augmented Gene…
Language Models are Universal Embedders
Xin Zhang, Zehan Li, Yanzhao Zhang +4
In the large language model (LLM) revolution, embedding is a key component of various systems, such as retrieving knowledge or memories for LLMs or building content moderation filt…
Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval
Dingkun Long, Qiong Gao, Kuan Zou +7
Passage retrieval is a fundamental task in information retrieval (IR) research, which has drawn much attention recently. In the English field, the availability of large-scale annot…
Knowledge Mechanisms in Large Language Models: A Survey and Perspective
Mengru Wang, Yunzhi Yao, Ziwen Xu +10
Understanding knowledge mechanisms in Large Language Models (LLMs) is crucial for advancing towards trustworthy AGI. This paper reviews knowledge mechanism analysis from a novel ta…
Prompt-Learning for Fine-Grained Entity Typing
Ning Ding, Yulin Chen, Xu Han +6
As an effective approach to tune pre-trained language models (PLMs) for specific tasks, prompt-learning has recently attracted much attention from researchers. By using \textit{clo…
Adversarial Self-Attention for Language Understanding
Hongqiu Wu, Ruixue Ding, Hai Zhao +3
Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness…
LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval
Jiajie Jin, Yanzhao Zhang, Mingxin Li +4
LLMs have fundamentally transformed dense retrieval, upgrading backbones from discriminative encoders to generative architectures. However, a critical disconnect remains: while LLM…
An Adaptive Framework for Generating Systematic Explanatory Answer in Online Q&A Platforms
Ziyang Chen, Xiaobin Wang, Yong Jiang +4
Question Answering (QA) systems face challenges in handling complex questions that require multi-domain knowledge synthesis. The naive RAG models, although effective in information…
EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation
Xin Guan, Xiaomeng Hu, Shen Huang +6
Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation remains profoundly challeng…
Keyphrase Extraction with Dynamic Graph Convolutional Networks and Diversified Inference
Haoyu Zhang, Dingkun Long, Guangwei Xu +3
Keyphrase extraction (KE) aims to summarize a set of phrases that accurately express a concept or a topic covered in a given document. Recently, Sequence-to-Sequence (Seq2Seq) base…
DeltaMem: Towards Agentic Memory Management via Reinforcement Learning
Qi Zhang, Shen Huang, Chu Liu +4
Recent advances in persona-centric memory have revealed the powerful capability of multi-agent systems in managing persona memory, especially in conversational scenarios. However,…
ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking
Yuzheng Cai, Yanzhao Zhang, Dingkun Long +3
Text reranking models are a crucial component in modern systems like Retrieval-Augmented Generation, tasked with selecting the most relevant documents prior to generation. However,…
AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis
Xuanzhong Chen, Zile Qiao, Guoxin Chen +7
Training large language model agents on tasks at the frontier of their capabilities is key to unlocking advanced reasoning. We introduce a data synthesis approach inspired by the e…
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Yanzhao Zhang, Mingxin Li, Dingkun Long +9
In this work, we introduce the Qwen3 Embedding series, a significant advancement over its predecessor, the GTE-Qwen series, in text embedding and reranking capabilities, built upon…
IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling
Guoxin Chen, Zile Qiao, Xuanzhong Chen +13
Recent advances in deep-research agents have shown promise for autonomous knowledge construction through dynamic reasoning over external sources. However, existing approaches rely…
DynamicBench: Evaluating Real-Time Report Generation in Large Language Models
Jingyao Li, Hao Sun, Zile Qiao +5
Traditional benchmarks for large language models (LLMs) typically rely on static evaluations through storytelling or opinion expression, which fail to capture the dynamic requireme…
Retrieved In-Context Principles from Previous Mistakes
Hao Sun, Yong Jiang, Bo Wang +4
In-context learning (ICL) has been instrumental in adapting Large Language Models (LLMs) to downstream tasks using correct input-output examples. Recent advances have attempted to…
CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding
Fuwei Zhang, Yanzhao Zhang, Mingxin Li +5
The paper presents CORE-Bench, a large benchmark designed to evaluate code retrieval tasks needed by coding agents, covering code understanding, issue-to-edit localization, and bro…
Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics
Maojia Song, Renhang Liu, Xinyu Wang +6
RAG (Retrieval-Augmented Generation) systems and web agents are increasingly evaluated on multi-hop deep search tasks, yet current practice suffers from two major limitations. Firs…
VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
Qiuchen Wang, Shihang Wang, Yu Zeng +9
Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retrieval-augmented Generation (RAG) metho…
Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling
Zile Qiao, Wei Ye, Yong Jiang +5
Retrieval-augmented language models (RALMs) have recently shown great potential in mitigating the limitations of implicit knowledge in LLMs, such as untimely updating of the latest…
Recall, Expand and Multi-Candidate Cross-Encode: Fast and Accurate Ultra-Fine Entity Typing
Chengyue Jiang, Wenyang Hui, Yong Jiang +3
Ultra-fine entity typing (UFET) predicts extremely free-formed types (e.g., president, politician) of a given entity mention (e.g., Joe Biden) in context. State-of-the-art (SOTA) m…
Hybrid Retrieval and Multi-stage Text Ranking Solution at TREC 2022 Deep Learning Track
Guangwei Xu, Yangzhao Zhang, Longhui Zhang +3
Large-scale text retrieval technology has been widely used in various practical business scenarios. This paper presents our systems for the TREC 2022 Deep Learning Track. We explai…
Parallel Instance Query Network for Named Entity Recognition
Yongliang Shen, Xiaobin Wang, Zeqi Tan +5
Named entity recognition (NER) is a fundamental task in natural language processing. Recent works treat named entity recognition as a reading comprehension task, constructing type-…
Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Process
Peng Wang, Xiaobin Wang, Chao Lou +3
In-context learning (ICL) is a few-shot learning paradigm that involves learning mappings through input-output pairs and appropriately applying them to new instances. Despite the r…
ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions
Jingheng Ye, Yong Jiang, Xiaobin Wang +5
This paper introduces the task of product demand clarification within an e-commercial scenario, where the user commences the conversation with ambiguous queries and the task-orient…
Qwen3Guard Technical Report
Haiquan Zhao, Chenhan Yuan, Fei Huang +40
As large language models (LLMs) become more capable and widely used, ensuring the safety of their outputs is increasingly critical. Existing guardrail models, though useful in stat…
Do PLMs Know and Understand Ontological Knowledge?
Weiqi Wu, Chengyue Jiang, Yong Jiang +2
Ontological knowledge, which comprises classes and properties and their relationships, is integral to world knowledge. It is significant to explore whether Pretrained Language Mode…
Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking
Yinghui Li, Yong Jiang, Yangning Li +4
Entity Linking (EL) is a fundamental task for Information Extraction and Knowledge Graphs. The general form of EL (i.e., end-to-end EL) aims to first find mentions in the given inp…
Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition
Xin Zhang, Guangwei Xu, Yueheng Sun +2
Crowdsourcing is regarded as one prospective solution for effective supervised learning, aiming to build large-scale annotated training data by crowd workers. Previous studies focu…
Improving General Text Embedding Model: Tackling Task Conflict and Data Imbalance through Model Merging
Mingxin Li, Zhijie Nie, Yanzhao Zhang +3
Text embeddings are vital for tasks such as text retrieval and semantic textual similarity (STS). Recently, the advent of pretrained language models, along with unified benchmarks…
DAMO-NLP at NLPCC-2022 Task 2: Knowledge Enhanced Robust NER for Speech Entity Linking
Shen Huang, Yuchen Zhai, Xinwei Long +4
Speech Entity Linking aims to recognize and disambiguate named entities in spoken languages. Conventional methods suffer gravely from the unfettered speech styles and the noisy tra…
Few-NERD: A Few-Shot Named Entity Recognition Dataset
Ning Ding, Guangwei Xu, Yulin Chen +5
Recently, considerable literature has grown up around the theme of few-shot named entity recognition (NER), but little published benchmark data specifically focused on the practica…
Exploring Key Point Analysis with Pairwise Generation and Graph Partitioning
Xiao Li, Yong Jiang, Shen Huang +3
Key Point Analysis (KPA), the summarization of multiple arguments into a concise collection of key points, continues to be a significant and unresolved issue within the field of ar…
WebSailor: Navigating Super-human Reasoning for Web Agent
Kuan Li, Zhongwang Zhang, Huifeng Yin +16
Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on…
EvolveSearch: An Iterative Self-Evolving Search Agent
Dingchu Zhang, Yida Zhao, Jialong Wu +8
The rapid advancement of large language models (LLMs) has transformed the landscape of agentic information seeking capabilities through the integration of tools such as search engi…
HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking
Yanzhao Zhang, Dingkun Long, Guangwei Xu +1
Deep pre-trained language models (e,g. BERT) are effective at large-scale text retrieval task. Existing text retrieval systems with state-of-the-art performance usually adopt a ret…
Challenging Decoder helps in Masked Auto-Encoder Pre-training for Dense Passage Retrieval
Zehan Li, Yanzhao Zhang, Dingkun Long +1
Recently, various studies have been directed towards exploring dense passage retrieval techniques employing pre-trained language models, among which the masked auto-encoder (MAE) p…
Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks
Xuming Hu, Yong Jiang, Aiwei Liu +5
Data augmentation techniques have been used to alleviate the problem of scarce labeled data in various NER tasks (flat, nested, and discontinuous NER tasks). Existing augmentation…
Improving Text Matching in E-Commerce Search with A Rationalizable, Intervenable and Fast Entity-Based Relevance Model
Jiong Cai, Yong Jiang, Yue Zhang +10
Discovering the intended items of user queries from a massive repository of items is one of the main goals of an e-commerce search system. Relevance prediction is essential to the…
ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
Xixi Wu, Kuan Li, Yida Zhao +13
Large Language Model (LLM)-based web agents excel at knowledge-intensive tasks but face a fundamental conflict between the need for extensive exploration and the constraints of lim…
Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum
Zhuoning Guo, Mingxin Li, Yanzhao Zhang +3
The prevailing video retrieval paradigm is structurally misaligned, as narrow benchmarks incentivize correspondingly limited data and single-task training. Therefore, universal cap…
RaFe: Ranking Feedback Improves Query Rewriting for RAG
Shengyu Mao, Yong Jiang, Boli Chen +7
As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream…
Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing
Tingyu Song, Yanzhao Zhang, Mingxin Li +6
Composed Image Retrieval (CIR) is a pivotal and complex task in multimodal understanding. Current CIR benchmarks typically feature limited query categories and fail to capture the…
KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models
Zhen Zhang, Xinyu Wang, Yong Jiang +7
Large Language Models (LLMs) often struggle with dynamically changing knowledge and handling unknown static information. Retrieval-Augmented Generation (RAG) is employed to tackle…
Prototypical Representation Learning for Relation Extraction
Ning Ding, Xiaobin Wang, Yao Fu +7
Recognizing relations between entities is a pivotal task of relational learning. Learning relation representations from distantly-labeled datasets is difficult because of the abund…
AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning
Shihao Cai, Runnan Fang, Jialong Wu +10
Conducting reinforcement learning (RL) in simulated environments offers a cost-effective and highly scalable way to enhance language-based agents. However, previous work has been l…
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
Peng Wang, Zexi Li, Ningyu Zhang +6
Large language models (LLMs) need knowledge updates to meet the ever-growing world facts and correct the hallucinated responses, facilitating the methods of lifelong model editing.…
E2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker
Qi Liu, Yanzhao Zhang, Mingxin Li +3
Text embedding models serve as a fundamental component in real-world search applications. By mapping queries and documents into a shared embedding space, they deliver competitive r…
Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-training
Longhui Zhang, Dingkun Long, Meishan Zhang +3
Chinese sequence labeling tasks are heavily reliant on accurate word boundary demarcation. Although current pre-trained language models (PLMs) have achieved substantial gains on th…
SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding
Tianyu Yu, Chengyue Jiang, Chao Lou +12
Large language models (LLMs) have shown impressive ability for open-domain NLP tasks. However, LLMs are sometimes too footloose for natural language understanding (NLU) tasks which…
SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response
Lehan Wang, Boli Chen, Ruixue Ding +7
The paper presents SecRespond, a benchmark that evaluates large language model agents on post-compromise incident‑response tasks using forensic disk snapshots, alerts, and vulnerab…
Memp: Exploring Agent Procedural Memory
Runnan Fang, Yuan Liang, Xiaobin Wang +6
Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In t…
VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
Qiuchen Wang, Ruixue Ding, Yu Zeng +6
Effectively retrieving, reasoning and understanding visually rich information remains a challenge for RAG methods. Traditional text-based methods cannot handle visual-related infor…
Text Representation Distillation via Information Bottleneck Principle
Yanzhao Zhang, Dingkun Long, Zehan Li +1
Pre-trained language models (PLMs) have recently shown great success in text representation field. However, the high computational cost and high-dimensional representation of PLMs…
Towards General Agentic Intelligence via Environment Scaling
Runnan Fang, Shihao Cai, Baixuan Li +13
Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-c…
Agent Planning with World Knowledge Model
Shuofei Qiao, Runnan Fang, Ningyu Zhang +7
Recent endeavors towards directly using large language models (LLMs) as agent models to execute interactive planning tasks have shown commendable results. Despite their achievement…