10 papers
RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios
Chenhao Yuan, Bohan Yu, Yinhao Xu +10
Large language models (LLMs) increasingly tackle complex real-world tasks in specialized domains. However, identifying and correctly applying domain-specific rules remains challeng…
Quantifying Error Tolerance in Synthetic Data: An Atomic-level Operand vs. Operator Perturbation Study
Jiaxiang Liu, Chenhao Yuan, Shuwen Xu +9
Synthetic data generation has become a cornerstone for advancing large language models. However, the lack of the quantitative analysis for error tolerance became a critical bottlen…
LongCrafter: Towards Diverse Long-Context Understanding via Evidence-Graph-Guided Instruction Synthesis
Chenhao Yuan, Yinhao Xu, Shuwen Xu +8
Synthesizing long-context supervised fine-tuning (SFT) data is a scalable way to enhance the long-context understanding of large language models (LLMs), yet existing approaches sha…
LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake
Haonan Wang, Jiaxiang Liu, Yurong Liu +11
Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can be trivially retrieved. In cont…
AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents
Yang Li, Jiaxiang Liu, Jiang Cai +1
A situated query like "where is Lin Wei?" often encodes more than its literal content: the user may also want to know whether Lin Wei is free, in a good mood, or worth interrupting…
GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum
Shuwen Xu, Yao Xu, Jiaxiang Liu +4
Agentic knowledge graph question answering (KGQA) requires an agent to iteratively interact with knowledge graphs (KGs), posing challenges in both training data scarcity and reason…
Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models
Jiaxiang Liu, Boxuan Xing, Chenhao Yuan +8
As large language models (LLMs) continue to advance, there is a growing urgency to enhance the interpretability of their internal knowledge mechanisms. Consequently, many interpret…
Capability Localization: Capabilities Can be Localized rather than Individual Knowledge
Xiusheng Huang, Jiaxiang Liu, Yequan Wang +2
Large scale language models have achieved superior performance in tasks related to natural language processing, however, it is still unclear how model parameters affect performance…
Reasons and Solutions for the Decline in Model Performance after Editing
Xiusheng Huang, Jiaxiang Liu, Yequan Wang +1
Knowledge editing technology has received widespread attention for low-cost updates of incorrect or outdated knowledge in large-scale language models. However, recent research has…
Enhancing Large Language Models with Pseudo- and Multisource- Knowledge Graphs for Open-ended Question Answering
Jiaxiang Liu, Tong Zhou, Yubo Chen +2
Mitigating the hallucinations of Large Language Models is a crucial task. Although some existing methods employ self-enhancement techniques, they fall short of effectively addressi…