Correctness is not Faithfulness in RAG Attributions

• URL: http://arxiv.org/abs/2412.18004v1
• Date: Mon, 23 Dec 2024 21:57:11 GMT
• Title: Correctness is not Faithfulness in RAG Attributions
• Authors: Jonas Wallat, Maria Heuss, Maarten de Rijke, Avishek Anand,
• Abstract summary: Explicitly citing source documents allows users to verify generated responses and increases trust.<n>Prior work largely evaluates citation correctness - whether cited documents support the corresponding statements.<n>To establish trust in attributed answers, we must examine both citation correctness and citation faithfulness.
• Score: 47.48625339105129
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieving relevant context is a common approach to reduce hallucinations and enhance answer reliability. Explicitly citing source documents allows users to verify generated responses and increases trust. Prior work largely evaluates citation correctness - whether cited documents support the corresponding statements. But citation correctness alone is insufficient. To establish trust in attributed answers, we must examine both citation correctness and citation faithfulness. In this work, we first disentangle the notions of citation correctness and faithfulness, which have been applied inconsistently in previous studies. Faithfulness ensures that the model's reliance on cited documents is genuine, reflecting actual reference use rather than superficial alignment with prior beliefs, which we call post-rationalization. We design an experiment that reveals the prevalent issue of post-rationalization, which undermines reliable attribution and may result in misplaced trust. Our findings suggest that current attributed answers often lack citation faithfulness (up to 57 percent of the citations), highlighting the need to evaluate correctness and faithfulness for trustworthy attribution in language models.

Related papers

• Is the Top Still Spinning? Evaluating Subjectivity in Narrative Understanding [50.94206345567363]
  Forcing binary labels upon ambiguous claims lowers the reliability of evaluation. We introduce LLM-generated edits of summaries as a method of providing a nuanced evaluation of claims. We show that ARM produces a absolute 21% improvement in annotator agreement on claim faithfulness.
  arXiv  Detail & Related papers  (2025-04-01T19:08:24Z)
• The Noisy Path from Source to Citation: Measuring How Scholars Engage with Past Research [20.649638393774048]
  We introduce a computational pipeline to quantify citation fidelity at scale. Using full texts of papers, the pipeline identifies citations in citing papers and the corresponding claims in cited papers. Using a quasi-experiment, we establish the "telephone effect" - when citing papers have low fidelity to the original claim, future papers that cite the citing paper and the original have lower fidelity to the original.
  arXiv  Detail & Related papers  (2025-02-27T22:47:03Z)
• Citations and Trust in LLM Generated Responses [6.69021669849899]
  Trust is predicted to be correlated with presence of citations and inversely related to checking citations. We tested this hypothesis with a live question-answering experiment that presented text responses generated using a commercial AI. We found a significant increase in trust when citations were present, a result that held true even when the citations were random.
  arXiv  Detail & Related papers  (2025-01-02T15:32:50Z)
• Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models [29.67884478799914]
  Large Language Models (LLMs) are capable of generating persuasive Natural Language Explanations (NLEs) to justify their answers. Recent studies have proposed various methods to measure the faithfulness of NLEs, typically by inserting perturbations at the explanation or feature level. We argue that these approaches are neither comprehensive nor correctly designed according to the established definition of faithfulness.
  arXiv  Detail & Related papers  (2024-10-18T03:45:42Z)
• Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data [48.409306245463]
  We develop models that quote verbatim statements from trusted sources in their pre-training data. The core of Quote-Tuning is a fast membership inference function that efficiently verifies text against trusted corpora. Experiments show that Quote-Tuning significantly increases verbatim quotes from high-quality documents by up to 130% relative to base models.
  arXiv  Detail & Related papers  (2024-04-05T02:27:09Z)
• Zero-shot Faithful Factual Error Correction [53.121642212060536]
  Faithfully correcting factual errors is critical for maintaining the integrity of textual knowledge bases and preventing hallucinations in sequence-to-sequence models. We present a zero-shot framework that formulates questions about input claims, looks for correct answers in the given evidence, and assesses the faithfulness of each correction based on its consistency with the evidence.
  arXiv  Detail & Related papers  (2023-05-13T18:55:20Z)
• Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence [59.81749318292707]
  We propose a fact verification model named ReRead to retrieve evidence and verify claim. The proposed system is able to achieve significant improvements upon best-reported models under different settings.
  arXiv  Detail & Related papers  (2023-05-02T03:23:14Z)
• Assessing Confidence with Assurance 2.0 [0.0]
  We argue that confidence cannot be reduced to a single attribute or measurement. Positive Perspectives consider the extent to which the evidence and overall argument of the case combine to make a positive statement. Negative Perspectives record doubts and challenges to the case, typically expressed as defeaters. Residual Doubts: the world is uncertain so not all potential defeaters can be resolved.
  arXiv  Detail & Related papers  (2022-05-03T22:10:59Z)
• Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness? [58.13152510843004]
  With the growing popularity of deep-learning based NLP models, comes a need for interpretable systems. What is interpretability, and what constitutes a high-quality interpretation? We call for more clearly differentiating between different desired criteria an interpretation should satisfy, and focus on the faithfulness criteria.
  arXiv  Detail & Related papers  (2020-04-07T20:15:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.