4 papers · 1 filter
YFPO: A Preliminary Study of Yoked Feature Preference Optimization with Neuron-Guided Rewards for Mathematical Reasoning
Yifan Le
Preference optimization has become an important post-training paradigm for improving the reasoning abilities of large language models. Existing methods typically rely on externally…
Schema Key Wording as an Instruction Channel in Structured Generation under Constrained Decoding
Yifan Le
Constrained decoding is widely used to make large language models produce structured outputs that satisfy schemas such as JSON. Existing work mainly treats schemas as structural co…
CRANE: Causal Relevance Analysis of Language-Specific Neurons in Multilingual Large Language Models
Yifan Le, Yunliang Li
Multilingual large language models (LLMs) achieve strong performance across languages, yet how language capabilities are organized at the neuron level remains poorly understood. Pr…
EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
Weikang Zhou, Xiao Wang, Limao Xiong +18
Jailbreak attacks are crucial for identifying and mitigating the security vulnerabilities of Large Language Models (LLMs). They are designed to bypass safeguards and elicit prohibi…