Pith. sign in

REVIEW 6 cited by

Towards Mitigating Hallucination in Large Language Models via Self-Reflection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.06271 v1 pith:DZQRORZQ submitted 2023-10-10 cs.CL cs.AI

Towards Mitigating Hallucination in Large Language Models via Self-Reflection

classification cs.CL cs.AI
keywords hallucinationanswersllmsmodelsapproachgenerativeissuelanguage
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large language models (LLMs) have shown promise for generative and knowledge-intensive tasks including question-answering (QA) tasks. However, the practical deployment still faces challenges, notably the issue of "hallucination", where models generate plausible-sounding but unfaithful or nonsensical information. This issue becomes particularly critical in the medical domain due to the uncommon professional concepts and potential social risks involved. This paper analyses the phenomenon of hallucination in medical generative QA systems using widely adopted LLMs and datasets. Our investigation centers on the identification and comprehension of common problematic answers, with a specific emphasis on hallucination. To tackle this challenge, we present an interactive self-reflection methodology that incorporates knowledge acquisition and answer generation. Through this feedback process, our approach steadily enhances the factuality, consistency, and entailment of the generated answers. Consequently, we harness the interactivity and multitasking ability of LLMs and produce progressively more precise and accurate answers. Experimental results on both automatic and human evaluation demonstrate the superiority of our approach in hallucination reduction compared to baselines.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Boosting Self-Consistency with Ranking

    cs.CL 2026-06 unverdicted novelty 6.0

    RISC reformulates self-consistency answer selection as a ranking task solved by a lightweight LambdaRank model with five hand-designed features, yielding better accuracy-efficiency trade-offs than majority voting on Q...

  2. Beyond Control-Flow: Integrating the Resource Perspective into Multi-Collaborative Process Modeling from Text

    cs.AI 2026-05 unverdicted novelty 6.0

    A resource-aware pipeline generates BPMN collaboration diagrams with pools and lanes from natural language descriptions using LLMs and a compact intermediate language.

  3. Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges

    cs.CL 2026-05 conditional novelty 6.0

    Per-bias selection of a cross-family LLM auditor lifts biased-judgment accuracy from 0.805/0.824 baselines to 0.884.

  4. Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs'Hallucinations

    cs.CL 2026-05 conditional novelty 6.0

    EAACD reduces hallucination in MoE LLMs by contrasting predictions of high-reliability expert groups against hallucination-amplified low-reliability expert groups.

  5. AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org

    cs.AI 2025-12 reject novelty 6.0

    An open-source agentic materials-design platform shows tool access can help or hurt accuracy depending on the property, but its headline memorization-resistant test results are not presented.

  6. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

    cs.CL 2023-11 unverdicted novelty 5.0

    The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.