activity
20242026
collaborators
Showing cs.CLShow all

21 papers · 1 filter

cs.CL2026

Thinking vs. NoThinking: Towards Interpreting Reasoning Mechanisms of Large Language Models via Sparse Autoencoders

Bo Cheng, Qiaolin Lu, Yi Chang +1

While Large Language Models (LLMs) employing Chain-of-Thought (CoT) exhibit superior reasoning capabilities, the neural mechanisms distinguishing this explicit Thinking mode from d…

cs.CL2026

BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models

Yupeng Chang, Yi Chang, Yuan Wu

Parameter-efficient fine-tuning (PEFT) has become a de facto standard for adapting large language models (LLMs). However, we identify a critical vulnerability within popular low-ra…

cs.CL2026

A Systematic Evaluation of Positional Bias in Multi-Video Summarization with MLLMs

Huangchen Xu, Yuan Wu, Yi Chang

Multimodal Large Language Models (MLLMs) are increasingly used for video understanding, yet their reliability under multi-video inputs remains poorly understood. We study positiona…

cs.CL2026

VCIFBench: Evaluating Complex Instruction Following for Video Understanding

Huangchen Xu, Yuan Wu, Yi Chang

Multimodal large language models have made rapid progress in video understanding, yet existing benchmarks largely rely on simple prompts and provide limited evidence about whether…

cs.CL2025

Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models

Jinzhe Li, Gengxu Li, Yi Chang +1

Large language models (LLMs) have witnessed rapid advancements, demonstrating remarkable capabilities. However, a notable vulnerability persists: LLMs often uncritically accept fla…

cs.CL2025

LoRA-MGPO: Mitigating Double Descent in Low-Rank Adaptation via Momentum-Guided Perturbation Optimization

Yupeng Chang, Chenlu Guo, Yi Chang +1

Parameter-efficient fine-tuning (PEFT), particularly Low-Rank Adaptation (LoRA), adapts large language models (LLMs) by training only a small fraction of parameters. However, as th…