Learning Fine-Grained Grounded Citations for Attributed Large Language Models
This addresses the issue of suboptimal citation quality and limited verifiability in attributed LLMs, offering an incremental improvement over existing methods.
The paper tackles the problem of hallucinations in attributed large language models by introducing FRONT, a training framework that teaches LLMs to generate fine-grained grounded citations using supporting quotes, resulting in a 14.21% average improvement in citation quality with LLaMA-2-7B.
Despite the impressive performance on information-seeking tasks, large language models (LLMs) still struggle with hallucinations. Attributed LLMs, which augment generated text with in-line citations, have shown potential in mitigating hallucinations and improving verifiability. However, current approaches suffer from suboptimal citation quality due to their reliance on in-context learning. Furthermore, the practice of citing only coarse document identifiers makes it challenging for users to perform fine-grained verification. In this work, we introduce FRONT, a training framework designed to teach LLMs to generate Fine-Grained Grounded Citations. By grounding model outputs in fine-grained supporting quotes, these quotes guide the generation of grounded and consistent responses, not only improving citation quality but also facilitating fine-grained verification. Experiments on the ALCE benchmark demonstrate the efficacy of FRONT in generating superior grounded responses and highly supportive citations. With LLaMA-2-7B, the framework significantly outperforms all the baselines, achieving an average of 14.21% improvement in citation quality across all datasets, even surpassing ChatGPT.