8 citations · 43 across the 33 of their papers we have counts for
28 papers · 1 filter
Mitigating Context Interference for Reliable and Efficient Search Agents
Boyang Xue, Bin Wu, Shuofei Qiao +8
Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved. However, the contexts…
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
Rui Wang, Hongru Wang, Yi Chen +4
On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systematic study examining the role, p…
WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models
Rui Wang, Ce Zhang, Jun-Yu Ma +10
The hallmark of Deep Research agents lies in compositional reasoning, the capacity to aggregate distributed, heterogeneous information into coherent logical insights. However, curr…
Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst
Hongru Wang, Deng Cai, Wanjun Zhong +4
Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length…
Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges
Hongru Wang, Wenyu Huang, Yufei Wang +7
Existing benchmarks that assess Language Models (LMs) as Language Agents (LAs) for tool use primarily focus on stateless, single-turn interactions or partial evaluations, such as t…
Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
Yiming Du, Wenyu Huang, Danna Zheng +5
Memory is fundamental to large language model (LLM)-based agents, but existing surveys emphasize application-level use (e.g., personalized dialogue), while overlooking the atomic o…
Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
Rui Wang, Hongru Wang, Boyang Xue +9
Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitioning from fast and intuitive thinking (Sy…
UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models
Boyang Xue, Fei Mi, Qi Zhu +6
Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where…
MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
Boyang Xue, Hongru Wang, Rui Wang +5
The tendency of Large Language Models (LLMs) to generate hallucinations raises concerns regarding their reliability. Therefore, confidence estimations indicating the extent of trus…
Analysing the Residual Stream of Language Models Under Knowledge Conflicts
Yu Zhao, Xiaotang Du, Giwon Hong +6
Large language models (LLMs) can store a significant amount of factual knowledge in their parameters. However, their parametric knowledge may conflict with the information provided…
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
Yu Zhao, Alessio Devoto, Giwon Hong +6
Large language models (LLMs) can store a significant amount of factual knowledge in their parameters. However, their parametric knowledge may conflict with the information provided…
SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation
Minda Hu, Licheng Zong, Hongru Wang +6
Large Language Models (LLMs) have shown great potential in the biomedical domain with the advancement of retrieval-augmented generation (RAG). However, existing retrieval-augmented…
UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrieval
Hongru Wang, Boyang Xue, Baohang Zhou +5
Conversational retrieval refers to an information retrieval system that operates in an iterative and interactive manner, requiring the retrieval of various external resources, such…
PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering
Yiming Du, Hongru Wang, Zhengyi Zhao +5
Long-term memory plays a critical role in personal interaction, considering long-term memory can better leverage world knowledge, historical information, and preferences in dialogu…
MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
Boyang Xue, Hongru Wang, Rui Wang +6
The tendency of Large Language Models (LLMs) to generate hallucinations raises concerns regarding their reliability. Therefore, confidence estimations indicating the extent of trus…
Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions
Hongru Wang, Boyang Xue, Baohang Zhou +5
Previous research has typically concentrated on leveraging the internal knowledge of Large Language Models (LLMs) to answer known questions (i.e., \textit{internal reasoning such a…
MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models
Wai-Chung Kwan, Xingshan Zeng, Yuxin Jiang +6
Large language models (LLMs) are increasingly relied upon for complex multi-turn conversations across diverse real-world applications. However, existing benchmarks predominantly fo…
UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems
Hongru Wang, Wenyu Huang, Yang Deng +6
Large Language Models (LLMs) has shown exceptional capabilities in many natual language understanding and generation tasks. However, the personalization issue still remains a much-…
Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment
Boyang Xue, Weichao Wang, Hongru Wang +7
Pretrained language models (PLMs) based knowledge-grounded dialogue systems are prone to generate responses that are factually inconsistent with the provided knowledge source. In s…
A Survey of the Evolution of Language Model-Based Dialogue Systems: Data, Task and Models
Hongru Wang, Lingzhi Wang, Yiming Du +4
Dialogue systems (DS), including the task-oriented dialogue system (TOD) and the open-domain dialogue system (ODD), have always been a fundamental task in natural language processi…
WatME: Towards Lossless Watermarking Through Lexical Redundancy
Liang Chen, Yatao Bian, Yang Deng +4
Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decodi…
Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogue
Hongru Wang, Minda Hu, Yang Deng +7
Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue sys…
Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators
Liang Chen, Yang Deng, Yatao Bian +4
Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks when being prompted to generate world knowledge. However, communit…
M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models
Wai-Chung Kwan, Xingshan Zeng, Yufei Wang +5
Managing long sequences has become an important and necessary feature for large language models (LLMs). However, it is still an open question of how to comprehensively and systemat…