collaborators

5 papers

cs.CL2026

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning

Haoyang Chen, Yi Liu, Jianzhi Shao +3

Thinking LLMs produce reasoning traces before answering. Prior activation steering work mainly targets on shaping these traces. It remains less understood how answer tokens actuall…

cs.AI2025

Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in Taiwan

Jui-Ming Yao, Bing-Cheng Xie, Sheng-Wei Peng +5

Multimodal Large Language Models (MLLMs) process visual, acoustic, and textual inputs, addressing the limitations of single-modality LLMs. However, existing benchmarks often overlo…

cs.CL2025

Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models

Jui-Ming Yao, Hao-Yuan Chen, Zi-Xian Tang +4

Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input pert…

cs.AI2025

Verbal Process Supervision Elicits Better Coding Agents

Hao-Yuan Chen, Cheng-Pong Huang, Jui-Ming Yao

The emergence of large language models and their applications as AI agents have significantly advanced state-of-the-art code generation benchmarks, transforming modern software eng…

cs.CL2025

Delta -- Contrastive Decoding Mitigates Text Hallucinations in Large Language Models

Cheng Peng Huang, Hao-Yuan Chen

Large language models (LLMs) demonstrate strong capabilities in natural language processing but remain prone to hallucinations, generating factually incorrect or fabricated content…