7 papers
Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding
Qiuyu Tian, Fengyi Chen, Yiding Li +9
Long-form narrative QA requires reasoning over evolving story worlds rather than isolated passages: answers may depend on earlier goals, changing character states, social relations…
Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
Junhao Liu, Haonan Yu, Zhenyu Yan +1
Post-hoc explanations provide transparency and are essential for guiding model optimization, such as prompt engineering and data sanitation. However, applying model-agnostic techni…
WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior
Haonan Yu, Junhao Liu, Zhenyu Yan +2
Precise behavioral control of large language models (LLMs) is critical for complex applications. However, existing methods often incur high training costs, lack natural language co…
Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards
Xin Zhang, Xingyu Li, Rongguang Wang +4
Accurate chart comprehension represents a critical challenge in advancing multimodal learning systems, as extensive information is compressed into structured visual representations…
Beyond Attribution: Unified Concept-Level Explanations
Junhao Liu, Haonan Yu, Xin Zhang
There is an increasing need to integrate model-agnostic explanation techniques with concept-based approaches, as the former can explain models across different architectures while…
Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection
Junhao Liu, Haonan Yu, Zhenyu Yan +1
As Large Language Models (LLMs) scale to handle massive context windows, achieving surgical feature-level interpretation is essential for high-stakes tasks like legal auditing and…