papers

Publications (41)

cs.IR2023

Text Matching Improves Sequential Recommendation by Reducing Popularity Biases

Zhenghao Liu, Sen Mei, Chenyan Xiong +5

This paper proposes Text mAtching based SequenTial rEcommendation model (TASTE), which maps items and users in an embedding space and recommends items by matching their text repres…

physics.soc-ph2019

Analysing Motifs in Multilayer Networks

Lu Zhong, Qingpeng Zhang, Dong Yang +2

Network motifs can capture basic interaction patterns and inform the functional properties of networks. However, real-world complex systems often have multiple types of relationshi…

cs.IR2020

CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search

Chenyan Xiong, Zhenghao Liu, Si Sun +7

Neural rankers based on deep pretrained language models (LMs) have been shown to improve many information retrieval benchmarks. However, these methods are affected by their the cor…

cs.LG2025

Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn

Chao Yu, Qixin Tan, Jiaxuan Gao +7

Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time…

cond-mat.quant-gas2017

Superadiabatic quantum friction suppression in finite-time thermodynamics

Shujin Deng, Aurélia Chenu, Pengpeng Diao +5

Optimal performance of thermal machines is reached by suppressing friction. Friction in quantum thermodynamics results from fast driving schemes that generate nonadiabatic excitati…

cs.AI2026

WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning

Zelai Xu, Zhexuan Xu, Ruize Zhang +7

Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use.…

cs.IR2025

UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation

Yuxuan Chen, Dewen Guo, Sen Mei +12

Retrieval-Augmented Generation (RAG) significantly enhances the performance of large language models (LLMs) in downstream tasks by integrating external knowledge. To facilitate res…

quant-ph2018

Shortcuts to adiabaticity in Fermi gases

Pengpeng Diao, Shujin Deng, Fang Li +4

Shortcuts to adiabaticity (STA) provide an alternative to adiabatic protocols to guide the dynamics of the system of interest without the requirement of slow driving. We report the…

cs.CL2025

DeepNote: Note-Centric Deep Retrieval-Augmented Generation

Ruobing Wang, Qingfei Zhao, Yukun Yan +9

Retrieval-Augmented Generation (RAG) mitigates factual errors and hallucinations in Large Language Models (LLMs) for question-answering (QA) by incorporating external knowledge. Ho…

cs.CL2021

Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning

Jerry Zikun Chen, Shi Yu, Haoran Wang

Query reformulation aims to alter noisy or ambiguous text sequences into coherent ones closer to natural language questions. This is to prevent errors from propagating in a client-…

cond-mat.quant-gas2017

Observation of Dynamical Super Efimovian Expansion in a Unitary Fermi Gas

Shujin Deng, Pengpeng Diao, Fang Li +3

We report an observation of a dynamical super Efimovian expansion in a two-component strongly interacting Fermi gas by engineering time dependent external harmonic trap frequencies…

math.RA2024

Towards the classification of finite-dimensional diagonally graded commutative algebras

Yunnan Li, Shi Yu

Any finite-dimensional commutative (associative) graded algebra with all nonzero homogeneous subspaces one-dimensional is defined by a symmetric coefficient matrix. This algebraic…

quant-ph2013

Suppressing phase decoherence of a single atom qubit with CPMG sequence

Shi Yu, Peng Xu, Xiaodong He +3

We experimentally demonstrate the strong suppression of dephasing of a qubit stored in a single \textsuperscript{87}Rb atom in an optical dipole trap by using Carr-Purcell-Meiboom-…

cs.IR2025

LISRec: Modeling User Preferences with Learned Item Shortcuts for Sequential Recommendation

Haidong Xin, Zhenghao Liu, Sen Mei +7

User-item interaction histories are pivotal for sequential recommendation systems but often include noise, such as unintended clicks or actions that fail to reflect genuine user pr…

cs.CL2024

Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression

Xinze Li, Zhenghao Liu, Chenyan Xiong +4

Large language models (LLMs) require lengthy prompts as the input context to produce output aligned with user intentions, a process that incurs extra costs during inference. In thi…

math.OC2020

Eigendecomposition of Q in Equally Constrained Quadratic Programming

Shi Yu

When applying eigenvalue decomposition on the quadratic term matrix in a type of linear equally constrained quadratic programming (EQP), there exists a linear mapping to project op…

cs.CL2026

CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning

Dingling Xu, Ruobing Wang, Qingfei Zhao +8

Reasoning Language Models (RLMs) have significantly improved performance on complex tasks by extending the reasoning chain. However, these chains are prone to containing factual er…

cs.CL2025

VisRAG2.0: Mitigating Visual Hallucinations via Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation

Yubo Sun, Chunyi Peng, Yukun Yan +6

Visual Retrieval-Augmented Generation (VRAG) has emerged as a promising paradigm for equipping Vision-Language Models (VLMs) with external visual evidence, enabling them to go beyo…

cs.CL2025

RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework

Kunlun Zhu, Yifan Luo, Dingling Xu +10

Retrieval-Augmented Generation (RAG) is a powerful approach that enables large language models (LLMs) to incorporate external knowledge. However, evaluating the effectiveness of RA…

cs.IR2025

Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking

Yifan Ji, Zhipeng Xu, Zhenghao Liu +7

Recent dense retrievers increasingly leverage the robust text understanding capabilities of Large Language Models (LLMs), encoding queries and documents into a shared embedding spa…

cs.CL2025

KBAlign: Efficient Self Adaptation on Specific Knowledge Bases

Zheni Zeng, Yuxuan Chen, Shi Yu +7

Although retrieval-augmented generation (RAG) remains essential for knowledge-based question answering (KBQA), current paradigms face critical challenges under specific domains. Ex…

cs.IR2024

Fusion-in-T5: Unifying Document Ranking Signals for Improved Information Retrieval

Shi Yu, Chenghao Fan, Chenyan Xiong +3

Common document ranking pipelines in search systems are cascade systems that involve multiple ranking layers to integrate different information step-by-step. In this paper, we prop…

cs.CL2023

Rethinking Dense Retrieval's Few-Shot Ability

Si Sun, Yida Lu, Shi Yu +6

Few-shot dense retrieval (DR) aims to effectively generalize to novel search scenarios by learning a few samples. Despite its importance, there is little study on specialized datas…

q-fin.PM2021

Learning Risk Preferences from Investment Portfolios Using Inverse Optimization

Shi Yu, Haoran Wang, Chaosheng Dong

The fundamental principle in Modern Portfolio Theory (MPT) is based on the quantification of the portfolio's risk related to performance. Although MPT has made huge impacts on the…

cs.CL2025

RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards

Xinze Li, Sen Mei, Zhenghao Liu +9

Retrieval-Augmented Generation (RAG) has proven its effectiveness in mitigating hallucinations in Large Language Models (LLMs) by retrieving knowledge from external resources. To a…

cs.CL2020

A Financial Service Chatbot based on Deep Bidirectional Transformers

Shi Yu, Yuxin Chen, Hussain Zaidi

We develop a chatbot using Deep Bidirectional Transformer models (BERT) to handle client questions in financial investment customer service. The bot can recognize 381 intents, and…

cs.CL2024

Building A Coding Assistant via the Retrieval-Augmented Language Model

Xinze Li, Hanbin Wang, Zhenghao Liu +6

Pretrained language models have shown strong effectiveness in code-related tasks, such as code retrieval, code generation, code summarization, and code completion tasks. In this pa…

cs.CL2025

Craw4LLM: Efficient Web Crawling for LLM Pretraining

Shi Yu, Zhiyuan Liu, Chenyan Xiong

Web crawl is a main source of large language models' (LLMs) pretraining data, but the majority of crawled web pages are discarded in pretraining due to low data quality. This paper…

cs.IR2022

P^3 Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning

Xiaomeng Hu, Shi Yu, Chenyan Xiong +3

Compared to other language tasks, applying pre-trained language models (PLMs) for search ranking often requires more nuances and training signals. In this paper, we identify and st…

cs.IR2020

Few-Shot Generative Conversational Query Rewriting

Shi Yu, Jiahua Liu, Jingqin Yang +4

Conversational query rewriting aims to reformulate a concise conversational query to a fully specified, context-independent query that can be effectively handled by existing inform…

cs.CL2025

KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG

Yongjian Li, HaoCheng Chu, Yukun Yan +7

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access broader knowledge sources, yet factual inconsistencies persist due to noise in retrieved documen…

quant-ph2023

Noisy intermediate-scale quantum computers

Bin Cheng, Xiu-Hao Deng, Xiu Gu +18

Quantum computers have made extraordinary progress over the past decade, and significant milestones have been achieved along the path of pursuing universal fault-tolerant quantum c…

cs.CL2024

Multi-Modal Multi-Granularity Tokenizer for Chu Bamboo Slip Scripts

Yingfa Chen, Chenlong Hu, Cong Feng +5

This study presents a multi-modal multi-granularity tokenizer specifically designed for analyzing ancient Chinese scripts, focusing on the Chu bamboo slip (CBS) script used during…

cs.IR2025

ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance

Sijia Yao, Pengcheng Huang, Zhenghao Liu +4

Large language models (LLMs) have demonstrated significant potential in enhancing dense retrieval through query augmentation. However, most existing methods treat the LLM and the r…

cs.CL2025

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts

Mingyan Wu, Zhenghao Liu, Yukun Yan +5

Retrieval-Augmented Generation (RAG) enhances the performance of Large Language Models (LLMs) by incorporating external knowledge. However, LLMs still encounter challenges in effec…

cs.IR2021

Few-Shot Conversational Dense Retrieval

Shi Yu, Zhenghao Liu, Chenyan Xiong +2

Dense retrieval (DR) has the potential to resolve the query understanding challenge in conversational search by matching in the learned embedding space. However, this adaptation is…

cs.IR2023

Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data

Xinze Li, Zhenghao Liu, Chenyan Xiong +4

This paper presents Structure Aware Dense Retrieval (SANTA) model, which encodes user queries and structured data in one universal embedding space for retrieving structured data. S…

cs.CL2023

Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In

Zichun Yu, Chenyan Xiong, Shi Yu +1

Retrieval augmentation can aid language models (LMs) in knowledge-intensive tasks by supplying them with external information. Prior works on retrieval augmentation usually jointly…

cs.IR2025

VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Shi Yu, Chaoyue Tang, Bokai Xu +8

Retrieval-augmented generation (RAG) is an effective technique that enables large language models (LLMs) to utilize external knowledge sources for generation. However, current RAG…

q-fin.PM2021

Robo-Advising: Enhancing Investment with Inverse Optimization and Deep Reinforcement Learning

Haoran Wang, Shi Yu

Machine Learning (ML) has been embraced as a powerful tool by the financial industry, with notable applications spreading in various domains including investment management. In thi…

cs.CL2026

ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling

Zhipeng Xu, Zhenghao Liu, Yukun Yan +7

Large Language Models (LLMs) have demonstrated strong performance across a wide range of NLP tasks. However, they often exhibit suboptimal behaviors and inconsistencies when expose…