Pith. sign in

REVIEW 6 cited by

KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking

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 2404.02935 v1 pith:4EWJMUMJ submitted 2024-04-03 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords knowledgeknowhalucheckingdetectingdetectionfactualhallucinationsllms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper introduces KnowHalu, a novel approach for detecting hallucinations in text generated by large language models (LLMs), utilizing step-wise reasoning, multi-formulation query, multi-form knowledge for factual checking, and fusion-based detection mechanism. As LLMs are increasingly applied across various domains, ensuring that their outputs are not hallucinated is critical. Recognizing the limitations of existing approaches that either rely on the self-consistency check of LLMs or perform post-hoc fact-checking without considering the complexity of queries or the form of knowledge, KnowHalu proposes a two-phase process for hallucination detection. In the first phase, it identifies non-fabrication hallucinations--responses that, while factually correct, are irrelevant or non-specific to the query. The second phase, multi-form based factual checking, contains five key steps: reasoning and query decomposition, knowledge retrieval, knowledge optimization, judgment generation, and judgment aggregation. Our extensive evaluations demonstrate that KnowHalu significantly outperforms SOTA baselines in detecting hallucinations across diverse tasks, e.g., improving by 15.65% in QA tasks and 5.50% in summarization tasks, highlighting its effectiveness and versatility in detecting hallucinations in LLM-generated content.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Collective Hallucination in Multi-Agent LLMs:Modeling and Defense

    cs.CR 2026-06 unverdicted novelty 5.0 of 10

    Models collective hallucinations in multi-agent LLMs as a diffusive process and demonstrates a control method that reduces hallucination rates by up to 39% in benchmark tests.

  2. Hallucination Cascade: Analyzing Error Propagation in Multi-Agent LLM Systems

    cs.CR 2026-06 unverdicted novelty 5.0 of 10

    Experiments reveal that multi-agent LLM cascades reduce hallucination scores but also slightly decrease factual accuracy.

  3. Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts

    cs.AI 2026-05 unverdicted novelty 5.0 of 10

    An A*-inspired multi-agent framework with hierarchical rewriting and a dynamic gamma parameter generates obfuscated prompts that achieve higher LLM attack success rates with fewer attempts than exhaustive search.

  4. MultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probing

    cs.CL 2026-05 unverdicted novelty 5.0 of 10

    MultiHaluDet uses multi-layer hidden-state probing, multi-scale attention, and a calibrated classifier ensemble to detect multilingual hallucinations, reporting up to 98.55% AUROC on English benchmarks and strong cros...

  5. MedFabric and EtHER: A Data-Centric Framework for Word-Level Fabrication Generation and Detection in Medical LLMs

    cs.CL 2026-05 unverdicted novelty 5.0 of 10

    MedFabric dataset and EtHER detector achieve over 15% better word-level fabrication detection in medical LLMs than prior methods by generating stylistically faithful errors and using decomposition-based checking.

  6. Hallucination Detection and Evaluation of Large Language Model

    cs.CL 2025-12 unverdicted novelty 4.0 of 10

    HHEM delivers fast hallucination detection in LLMs via classification, cutting evaluation time from 8 hours to 10 minutes with up to 82.2% accuracy while adding segment retrieval for summarization.

Pith tools