10 papers
CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering
Zhichao Yan, Shizhao Li, Jiapu Wang +5
Long-form question answering increasingly relies on retrieved evidence to make LLM outputs verifiable, with inline citations tracing claims to source documents. However, existing s…
Chain Of Thought Compression: A Theoretical Analysis
Juncai Li, Ru Li, Yuxiang Zhou +2
Chain-of-Thought (CoT) has unlocked advanced reasoning abilities of Large Language Models (LLMs) with intermediate steps, yet incurs prohibitive computational costs due to generati…
Beyond Factual Accuracy: Evaluating Global Reasoning Integrity in RAG Systems with LogicScore
Zhichao Yan, Yunxiao Zhao, Jiapu Wang +4
Current evaluation methods for Retrieval Augmented Generation (RAG) suffer from \textit{factual myopia}: they relentlessly emphasize factual accuracy yet neglect global logical int…
Plan Then Retrieve: Reinforcement Learning-Guided Complex Reasoning over Knowledge Graphs
Yanlin Song, Ben Liu, VÃctor Gutiérrez-Basulto +5
Knowledge Graph Question Answering aims to answer natural language questions by reasoning over structured knowledge graphs. While large language models have advanced KGQA through t…
Consistency-Aware Editing for Entity-level Unlearning in Language Models
Xiaoqi Han, VÃctor Gutiérrez-Basulto, Ru Li +3
Large language models (LLMs) risk retaining sensitive, copyrighted, or harmful information from their training data. Entity-level unlearning addresses this issue by removing all kn…
Uncovering and Mitigating Transient Blindness in Multimodal Model Editing
Xiaoqi Han, Ru Li, Ran Yi +4
Multimodal Model Editing (MMED) aims to correct erroneous knowledge in multimodal models. Existing evaluation methods, adapted from textual model editing, overstate success by rely…