8 papers
Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Reranking
Peijia Guo, Wenxuan Xie, ZiGuang Li +1
Large language models (LLMs) pose challenges to academic integrity and peer review. Yet generative plagiarism detection remains an underexplored and largely unresolved challenge. P…
Beyond Facts: Benchmarking Distributional Reading Comprehension in Large Language Models
Pei-Fu Guo, Ya-An Tsai, Chun-Chia Hsu +6
While most reading comprehension benchmarks for LLMs focus on factual information that can be answered by localizing specific textual evidence, many real-world tasks require unders…
LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs
Pei-Fu Guo, Yun-Da Tsai, Chun-Chia Hsu +6
Evaluating cross-lingual knowledge transfer in large language models is challenging, as correct answers in a target language may arise either from genuine transfer or from prior ex…
Uncertainty Profiles for LLMs: Uncertainty Source Decomposition and Adaptive Model-Metric Selection
Pei-Fu Guo, Yun-Da Tsai, Shou-De Lin
Large language models (LLMs) often generate fluent but factually incorrect outputs, known as hallucinations, which undermine their reliability in real-world applications. While unc…
Benchmarking Large Language Model Uncertainty for Prompt Optimization
Pei-Fu Guo, Yun-Da Tsai, Shou-De Lin
Prompt optimization algorithms for Large Language Models (LLMs) excel in multi-step reasoning but still lack effective uncertainty estimation. This paper introduces a benchmark dat…
Ranking LLMs by compression
Peijia Guo, Ziguang Li, Haibo Hu +3
We conceptualize the process of understanding as information compression, and propose a method for ranking large language models (LLMs) based on lossless data compression. We demon…