Pith. sign in

REVIEW 8 cited by

Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models

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 2407.08039 v1 pith:WHAAMI2J submitted 2024-07-10 cs.CL

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

Hallucination is often regarded as a major impediment for using large language models (LLMs), especially for knowledge-intensive tasks. Even when the training corpus consists solely of true statements, language models still generate hallucinations in the form of amalgamations of multiple facts. We coin this phenomenon as ``knowledge overshadowing'': when we query knowledge from a language model with multiple conditions, some conditions overshadow others, leading to hallucinated outputs. This phenomenon partially stems from training data imbalance, which we verify on both pretrained models and fine-tuned models, over a wide range of LM model families and sizes.From a theoretical point of view, knowledge overshadowing can be interpreted as over-generalization of the dominant conditions (patterns). We show that the hallucination rate grows with both the imbalance ratio (between the popular and unpopular condition) and the length of dominant condition description, consistent with our derived generalization bound. Finally, we propose to utilize overshadowing conditions as a signal to catch hallucination before it is produced, along with a training-free self-contrastive decoding method to alleviate hallucination during inference. Our proposed approach showcases up to 82% F1 for hallucination anticipation and 11.2% to 39.4% hallucination control, with different models and datasets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Verbalizable Representations Form a Global Workspace in Language Models

    cs.CL 2026-07 conditional novelty 7.0 of 10

    Language models represent their current reasoning in a small, readable set of verbalizable vectors (the J-space) that functions like a global workspace.

  2. Exploring Causal Effect of Social Bias on Faithfulness Hallucinations in Large Language Models

    cs.CL 2025-08 conditional novelty 6.0 of 10

    Social bias is a statistically significant cause of faithfulness hallucinations in LLMs, with anti-stereotypical contexts increasing errors and pro-stereotypical contexts decreasing them.

  3. Beyond Facts: Evaluating Intent Hallucination in Large Language Models

    cs.CL 2025-06 reject novelty 6.0 of 10

    The paper proposes a query-centric evaluation of LLM "intent hallucination" via constraint decomposition, but the headline metric comparison is undermined by a self-referential human evaluation design.

  4. Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis

    cs.CL 2025-05 conditional novelty 6.0 of 10

    PhantomCircuit traces knowledge overshadowing to attention circuits during training and prunes circuit edges to recover the overshadowed answer.

  5. Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor

    cs.LG 2025-07 reject novelty 4.0 of 10

    A black-box hallucination watchdog that stores previously hallucinated queries in a vector database and flags new queries by embedding similarity and semantic entropy.

  6. A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction

    cs.CL 2025-05 conditional novelty 4.0 of 10

    A graph of small fine-tuned Llama experts with isolated training chunks scores 3x higher exact match than a single 8B model on Cessna repair-manual QA, but with lower ROUGE-L and METEOR.

  7. Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models

    cs.CL 2025-06 reject novelty 3.0 of 10

    A survey of LLM hallucination research that formalizes hallucination types and argues, via incompleteness and undecidability arguments, that hallucinations cannot be fully eliminated.

  8. A comprehensive taxonomy of hallucinations in Large Language Models

    cs.CL 2025-08 conditional novelty 2.0 of 10

    A survey that organizes LLM hallucination types, causes, benchmarks, and mitigations, and restates the theorem that hallucination is inevitable for computable LLMs.

Pith tools