Effective Large Language Model Adaptation for Improved Grounding and Citation Generation

Xi Ye, Ruoxi Sun, Sercan Ö. Arik, Tomas Pfister

Presented at ACL 2024, the AGREE (Adaptation for GRounding EnhancEment) framework represents a collaborative effort between UT Austin and Google Cloud AI. AGREE addresses the critical need for reliability in Large Language Models (LLMs) by training them to self-ground claims and provide accurate, verifiable citations.

The Grounding Challenge in RAG

Retrieval-Augmented Generation (RAG) is a common technique to mitigate hallucinations by providing external context. However, current RAG systems face two primary limitations:

  1. Citation Hallucination: Standard prompting often leads to citations that do not actually support the generated claims or point to incorrect passages.
  2. Static Retrieval: Most systems retrieve documents once. If the initial retrieval is insufficient, the model lacks a mechanism to seek further information, leading to failure or fabrication.

Existing post-hoc solutions attempt to verify citations after generation, but these are computationally expensive and rely heavily on the model's internal knowledge during the initial generation phase.

The AGREE Framework

AGREE is a learning-based framework that integrates grounding directly into the model's generation process. It consists of two distinct phases: Training Adaptation and Test-Time Adaptation.

The AGREE framework overview, contrasting its learning-based approach with prompting-based and post-hoc citing methods.

Training Adaptation: Learning to Cite

The training phase focuses on fine-tuning the LLM to generate grounded responses with inline citations. To avoid the high cost of human labeling, the authors developed an automated "self-improvement" loop:

  • Data Construction: Candidate responses are generated from unlabeled queries using a base LLM.
  • NLI Filtering: An external Natural Language Inference (NLI) model (specifically the TRUE model) evaluates every sentence against retrieved passages.
  • Fine-Tuning: The model is fine-tuned using Parameter-Efficient Fine-Tuning (LoRA) on the highest-quality grounded data. A key innovation is teaching the model to explicitly list "Claims Not Supported" at the end of its response.
The tuning process overview and a concrete example of the generated training data, including unsupported statements.

Test-Time Adaptation (TTA)

During inference, AGREE employs an iterative refinement strategy. If the model identifies unsupported statements in its initial output, it uses those statements as specific search queries to retrieve better evidence. The response is then regenerated, continuing for up to four iterations or until all claims are grounded.

Experimental Evaluation

The researchers evaluated AGREE across five diverse datasets, including fact-checking (FEVER), multi-hop reasoning (StrategyQA), and ambiguous questions (ASQA). Testing also included an out-of-distribution (OOD) proprietary Enterprise dataset for customer support.

Key Insights and Results

  • Precision and Recall: AGREE achieved over a 20% improvement in citation precision and recall compared to standard prompting-based approaches.
  • Self-Awareness as a Trigger: Training the model to recognize what it doesn't know (unsupported claims) is crucial for triggering the iterative TTA loop.
  • Effective Distillation: Smaller models, such as Llama-2-13b, were successfully tuned using data generated by larger models like Google's text-bison, allowing them to rival the performance of much larger proprietary models.
  • Zero-Shot Generalization: Models tuned on general Wikipedia-based tasks demonstrated strong grounding capabilities when applied to the specialized Enterprise dataset without further domain-specific tuning.

Conclusion

AGREE demonstrates that grounding and citation generation are learnable skills that significantly enhance LLM reliability. By combining automated data construction with iterative test-time refinement, the framework provides a scalable path toward more trustworthy AI systems that can verify their own claims.

Summary updated

Abstract

Large language models (LLMs) have achieved remarkable advancements in natural language understanding and generation. However, one major issue towards their widespread deployment in the real world is that they can generate “hallucinated” answers that are not factual.Towards this end, this paper focuses on improving LLMs by grounding their responses in retrieved passages and by providing citations. We propose a new framework, AGREE, Adaptation for GRounding EnhancEment, that improves the grounding from a holistic perspective. Our framework tunes LLMs to self-ground the claims in their responses and provide accurate citations to retrieved documents. This tuning on top of the pre-trained LLMs requires well-grounded responses (with citations) for paired queries, for which we introduce a method that can automatically construct such data from unlabeled queries. The self-grounding capability of tuned LLMs further grants them a test-time adaptation (TTA) capability that can actively retrieve passages to support the claims that have not been grounded, which iteratively improves the responses of LLMs. Across five datasets and two LLMs, our results show that the proposed tuning-based framework generates superior grounded responses with more accurate citations compared to prompting-based approaches and post-hoc citing-based approaches.
BibTeX
@inproceedings{ye2024effective,
  author = {Xi Ye and Ruoxi Sun and Sercan Ö. Arik and Tomas Pfister},
  title = {{Effective Large Language Model Adaptation for Improved Grounding and Citation Generation}},
  booktitle = {Conference of the North American Chapter of the Association for Computational Linguistics},
  year = {2024},
  doi = {10.18653/v1/2024.naacl-long.346},
}
Figure