Pre-trained Language Models Return Distinguishable Probability Distributions to Unfaithfully Hallucinated Texts
Autor: | Cha, Taehun, Lee, Donghun |
---|---|
Rok vydání: | 2024 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | In this work, we show the pre-trained language models return distinguishable generation probability and uncertainty distribution to unfaithfully hallucinated texts, regardless of their size and structure. By examining 24 models on 6 data sets, we find out that 88-98% of cases return statistically significantly distinguishable generation probability and uncertainty distributions. Using this general phenomenon, we showcase a hallucination-reducing training algorithm. Our algorithm outperforms other baselines by achieving higher faithfulness metrics while maintaining sound general text quality measures. Comment: 10 pages, EMNLP 2024 Findings |
Databáze: | arXiv |
Externí odkaz: |