9 papers
Learning When to Trust via Selective Context Preference Optimization
Xian Sun, Wei Chow, Yingshuo Wang +4
Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, training models to resist…
Guiding LLM-based Loop Invariant Synthesis via Feedback on Local Reasoning Errors
Tianchi Li, Zhenyu Yan, Junhao Liu +2
We propose a novel framework that provides constructive feedback to an LLM in the "guess-and-check" paradigm by formally verifying its own thinking process and detecting local reas…
Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis
Zhenhao Xu, Wenhan Chang, Yichuan Chen +3
Large Reasoning Models (LRMs) improve performance on complex tasks, but they also make safety control harder at deployment time. In black-box settings, defenders cannot modify mode…
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…
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…