2024 TrainingLanguageModelstoGenerat

From GM-RKB
(Redirected from Huang et al., 2024)
Jump to navigation Jump to search

Subject Headings: Fine-Grained Rewarding, LLM Hallucination.

Notes

Cited By

Quotes

Abstract

While recent Large Language Models (LLMs) have proven useful in answering user queries, they are prone to hallucination, and their responses often lack credibility due to missing references to reliable sources. An intuitive solution to these issues would be to include in-text citations referring to external documents as evidence. While previous works have directly prompted LLMs to generate in-text citations, their performances are far from satisfactory, especially when it comes to smaller LLMs. In this work, we propose an effective training framework using fine-grained rewards to teach LLMs to generate highly supportive and relevant citations, while ensuring the correctness of their responses. We also conduct a systematic analysis of applying these fine-grained rewards to common LLM training strategies, demonstrating its advantage over conventional practices. We conduct extensive experiments on Question Answering (QA) datasets taken from the ALCE benchmark and validate the model's generalizability using EXPERTQA. On LLaMA-2-7B, the incorporation of fine-grained rewards achieves the best performance among the baselines, even surpassing that of GPT-3.5-turbo.

References

;

 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2024 TrainingLanguageModelstoGeneratChengyu Huang
Zeqiu Wu
Yushi Hu
Wenya Wang
Training Language Models to Generate Text with Citations via Fine-grained Rewards10.48550/arXiv.2402.043152024