DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Autor:	Chuang, Yung-Sung, Xie, Yujia, Luo, Hongyin, Kim, Yoon, Glass, James, He, Pengcheng
Rok vydání:	2023
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Despite their impressive capabilities, large language models (LLMs) are prone to hallucinations, i.e., generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations with pretrained LLMs that does not require conditioning on retrieved external knowledge nor additional fine-tuning. Our approach obtains the next-token distribution by contrasting the differences in logits obtained from projecting the later layers versus earlier layers to the vocabulary space, exploiting the fact that factual knowledge in an LLMs has generally been shown to be localized to particular transformer layers. We find that this Decoding by Contrasting Layers (DoLa) approach is able to better surface factual knowledge and reduce the generation of incorrect facts. DoLa consistently improves the truthfulness across multiple choices tasks and open-ended generation tasks, for example improving the performance of LLaMA family models on TruthfulQA by 12-17% absolute points, demonstrating its potential in making LLMs reliably generate truthful facts. Comment: ICLR 2024 main conference paper. The source code is available at https://github.com/voidism/DoLa
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2309.03883 Zobrazit plný text záznamu View this record from Arxiv