按年被提到
20242024 · 2 次2026
大模型与语言模型›大模型评测与真实性·arXiv:2402.04315 · cs.CL

Training Language Models to Generate Text with Citations via Fine-grained Rewards

Chengyu Huang, Zeqiu Wu, Yushi Hu, Wenya Wang · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-02-16 · 最近 2024-04-21
2不同的人
2活跃月份
2讨论串
17被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论neodypsis · 2024-04

“Could something like that proposed in "Training Language Models to Generate Text with Citations via Fine-grained Rewards" [0] work for you? 0. https://arxiv.org/abs/2402.04315”

Financial market applications of LLMs原评论 ↗
被提交为 story · 1 次