Citations and Trust in LLM Generated Responses

• URL: http://arxiv.org/abs/2501.01303v1
• Date: Thu, 02 Jan 2025 15:32:50 GMT
• Title: Citations and Trust in LLM Generated Responses
• Authors: Yifan Ding, Matthew Facciani, Amrit Poudel, Ellen Joyce, Salvador Aguinaga, Balaji Veeramani, Sanmitra Bhattacharya, Tim Weninger,
• Abstract summary: 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.
• Score: 6.69021669849899
• License:
• Abstract: Question answering systems are rapidly advancing, but their opaque nature may impact user trust. We explored trust through an anti-monitoring framework, where 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 Chatbot along with varying citations (zero, one, or five), both relevant and random, and recorded if participants checked the citations and their self-reported trust in the generated responses. We found a significant increase in trust when citations were present, a result that held true even when the citations were random; we also found a significant decrease in trust when participants checked the citations. These results highlight the importance of citations in enhancing trust in AI-generated content.

Related papers

• SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models [51.90867482317985]
  SelfCite is a self-supervised approach that aligns LLMs to generate high-quality, fine-grained, sentence-level citations for statements in generated responses. Instead of relying on costly and labor-intensive annotations, SelfCite leverages a reward signal provided by the LLM itself through context ablation. The effectiveness of SelfCite is demonstrated by increasing citation F1 up to 5.3 points on the LongBench-Cite benchmark across five long-form question answering tasks.
  arXiv  Detail & Related papers  (2025-02-13T18:55:13Z)
• Correctness is not Faithfulness in RAG Attributions [47.48625339105129]
  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. To establish trust in attributed answers, we must examine both citation correctness and citation faithfulness.
  arXiv  Detail & Related papers  (2024-12-23T21:57:11Z)
• 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)
• TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness [58.721012475577716]
  Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, prompting a surge in their practical applications. This paper introduces TrustScore, a framework based on the concept of Behavioral Consistency, which evaluates whether an LLMs response aligns with its intrinsic knowledge.
  arXiv  Detail & Related papers  (2024-02-19T21:12:14Z)
• RELIC: Investigating Large Language Model Responses using Self-Consistency [58.63436505595177]
  Large Language Models (LLMs) are notorious for blending fact with fiction and generating non-factual content, known as hallucinations. We propose an interactive system that helps users gain insight into the reliability of the generated text.
  arXiv  Detail & Related papers  (2023-11-28T14:55:52Z)
• The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question Answering [20.439568097395995]
  We show that task-based systems which exhibit certain advanced linguistic dialog behaviors, such as lexical alignment, are in fact preferred and trusted more. Our results highlight the danger of systems that appear to be trustworthy by parroting user input while providing an unfaithful response.
  arXiv  Detail & Related papers  (2023-05-25T22:54:13Z)
• Evaluating Verifiability in Generative Search Engines [70.59477647085387]
  Generative search engines directly generate responses to user queries, along with in-line citations. We conduct human evaluation to audit four popular generative search engines. We find that responses from existing generative search engines are fluent and appear informative, but frequently contain unsupported statements and inaccurate citations.
  arXiv  Detail & Related papers  (2023-04-19T17:56:12Z)
• Correcting Exposure Bias for Link Recommendation [31.799185352323807]
  Exposure bias can arise when users are systematically underexposed to certain relevant items. We propose estimators that leverage known exposure probabilities to mitigate this bias. Our methods lead to greater diversity in the recommended papers' fields of study.
  arXiv  Detail & Related papers  (2021-06-13T16:51:41Z)

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.