RELIC: Investigating Large Language Model Responses using Self-Consistency

• URL: http://arxiv.org/abs/2311.16842v2
• Date: Thu, 4 Apr 2024 15:18:30 GMT
• Title: RELIC: Investigating Large Language Model Responses using Self-Consistency
• Authors: Furui Cheng, Vilém Zouhar, Simran Arora, Mrinmaya Sachan, Hendrik Strobelt, Mennatallah El-Assady,
• Abstract summary: 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.
• Score: 58.63436505595177
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) are notorious for blending fact with fiction and generating non-factual content, known as hallucinations. To address this challenge, we propose an interactive system that helps users gain insight into the reliability of the generated text. Our approach is based on the idea that the self-consistency of multiple samples generated by the same LLM relates to its confidence in individual claims in the generated texts. Using this idea, we design RELIC, an interactive system that enables users to investigate and verify semantic-level variations in multiple long-form responses. This allows users to recognize potentially inaccurate information in the generated text and make necessary corrections. From a user study with ten participants, we demonstrate that our approach helps users better verify the reliability of the generated text. We further summarize the design implications and lessons learned from this research for future studies of reliable human-LLM interactions.

Related papers

• CLEAR-KGQA: Clarification-Enhanced Ambiguity Resolution for Knowledge Graph Question Answering [13.624962763072899]
  KGQA systems typically assume user queries are unambiguous, which is an assumption that rarely holds in real-world applications. We propose a novel framework that dynamically handles both entity ambiguity (e.g., distinguishing between entities with similar names) and intent ambiguity (e.g., clarifying different interpretations of user queries) through interactive clarification.
  arXiv  Detail & Related papers  (2025-04-13T17:34:35Z)
• Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future to eDemorcacy [5.92971970173011]
  This paper investigates the use of Large Language Models to synthesize public opinion data. It addresses challenges in traditional survey methods like declining response rates and non-response bias. We introduce a novel technique: role creation based on knowledge injection.
  arXiv  Detail & Related papers  (2025-03-31T21:21:52Z)
• Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies [66.30619782227173]
  Large language models (LLMs) can produce erroneous responses that sound fluent and convincing. We identify several features of LLM responses that shape users' reliance. We find that explanations increase reliance on both correct and incorrect responses. We observe less reliance on incorrect responses when sources are provided or when explanations exhibit inconsistencies.
  arXiv  Detail & Related papers  (2025-02-12T16:35:41Z)
• Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization [35.269343563526675]
  We propose RHIO, a framework to teach large language models to explicitly discriminate between faithful and unfaithful generations. RHIO first augments unfaithful samples that simulate realistic model-intrinsic errors by selectively masking retrieval heads. These samples are incorporated into joint training, enabling the model to distinguish unfaithful outputs from faithful ones conditioned on control tokens.
  arXiv  Detail & Related papers  (2025-01-23T11:23:25Z)
• Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions [35.48507905027844]
  Humans increasingly rely on large language models (LLMs) LLMs are susceptible to generating inaccurate or false information, also known as "hallucinations"
  arXiv  Detail & Related papers  (2024-05-30T19:23:14Z)
• Interactive Analysis of LLMs using Meaningful Counterfactuals [22.755345889167934]
  Counterfactual examples are useful for exploring the decision boundaries of machine learning models. How can we apply counterfactual-based methods to analyze and explain LLMs? We propose a novel algorithm for generating batches of complete and meaningful textual counterfactuals. In our experiments, 97.2% of the counterfactuals are grammatically correct.
  arXiv  Detail & Related papers  (2024-04-23T19:57:03Z)
• Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment [77.56326872997407]
  Pretrained language models (PLMs) based knowledge-grounded dialogue systems are prone to generate responses that are factually inconsistent with the provided knowledge source. Inspired by previous work which identified that feed-forward networks (FFNs) within Transformers are responsible for factual knowledge expressions, we investigate two methods to efficiently improve the factual expression capability.
  arXiv  Detail & Related papers  (2023-10-12T14:44:05Z)
• Self-Convinced Prompting: Few-Shot Question Answering with Repeated Introspection [13.608076739368949]
  We introduce a novel framework that harnesses the potential of large-scale pre-trained language models. Our framework processes the output of a typical few-shot chain-of-thought prompt, assesses the correctness of the response, scrutinizes the answer, and ultimately produces a new solution.
  arXiv  Detail & Related papers  (2023-10-08T06:36:26Z)
• Ask Again, Then Fail: Large Language Models' Vacillations in Judgment [28.74246375289661]
  We observe that current conversational language models often waver in their judgments when faced with follow-up questions. We introduce a textscFollow-up Questioning Mechanism along with two metrics to quantify this inconsistency. We develop a training-based framework textscUnwavering-FQ that teaches language models to maintain their originally correct judgments.
  arXiv  Detail & Related papers  (2023-10-03T16:08:41Z)
• PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems [59.1250765143521]
  Current knowledge-grounded dialogue systems often fail to align the generated responses with human-preferred qualities. We propose Polished & Informed Candidate Scoring (PICK), a generation re-scoring framework. We demonstrate the effectiveness of PICK in generating responses that are more faithful while keeping them relevant to the dialogue history.
  arXiv  Detail & Related papers  (2023-09-19T08:27:09Z)
• Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference [82.28542500317445]
  We present an end-to-end learning framework, termed Sequential Posterior Inference (SPI), capable of selecting knowledge and generating dialogues. Unlike other methods, SPI does not require the inference network or assume a simple geometry of the posterior distribution.
  arXiv  Detail & Related papers  (2023-06-01T21:23:13Z)
• Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback [57.816210168909286]
  We leverage recent progress on textual entailment models to address this problem for abstractive summarization systems. We use reinforcement learning with reference-free, textual entailment rewards to optimize for factual consistency. Our results, according to both automatic metrics and human evaluation, show that our method considerably improves the faithfulness, salience, and conciseness of the generated summaries.
  arXiv  Detail & Related papers  (2023-05-31T21:04:04Z)
• SWING: Balancing Coverage and Faithfulness for Dialogue Summarization [67.76393867114923]
  We propose to utilize natural language inference (NLI) models to improve coverage while avoiding factual inconsistencies. We use NLI to compute fine-grained training signals to encourage the model to generate content in the reference summaries that have not been covered. Experiments on the DialogSum and SAMSum datasets confirm the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2023-01-25T09:33:11Z)

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.