Pei-Fu Guo

2 accepted papers

2025

Benchmarking Uncertainty Metrics for LLM Target-Aware Search

EMNLP 2025

LLM search methods, such as Chain of Thought (CoT) and Tree of Thought (ToT), enhance LLM reasoning by exploring multiple reasoning paths. When combined with search algorithms like MCTS and Bandit methods, their effectiveness relies heavily on uncertainty estimation to prioritize paths that align wi

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Text-centric Alignment for Bridging Test-time Unseen Modality

Yun-Da Tsai, Ting-Yu Yen, Pei-Fu Guo, Zhe-Yan Li, Shou-De Lin

EMNLP 2025

This paper addresses the challenge of handling unseen modalities and dynamic modality combinations at test time with our proposed text-centric alignment method. This training-free alignment approach unifies different input modalities into a single semantic text representation by leveraging in-contex

Cited by 0 Source ↗PDF ↗Scholar ↗