Pith. sign in

REVIEW 5 cited by

On Hallucination and Predictive Uncertainty in Conditional Language Generation

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 2103.15025 v1 pith:P6B5JL6F submitted 2021-03-28 cs.CL

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

Despite improvements in performances on different natural language generation tasks, deep neural models are prone to hallucinating facts that are incorrect or nonexistent. Different hypotheses are proposed and examined separately for different tasks, but no systematic explanations are available across these tasks. In this study, we draw connections between hallucinations and predictive uncertainty in conditional language generation. We investigate their relationship in both image captioning and data-to-text generation and propose a simple extension to beam search to reduce hallucination. Our analysis shows that higher predictive uncertainty corresponds to a higher chance of hallucination. Epistemic uncertainty is more indicative of hallucination than aleatoric or total uncertainties. It helps to achieve better results of trading performance in standard metric for less hallucination with the proposed beam search variant.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 16 citations worldwide. Full citation record

  1. HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling

    cs.LG 2025-09 conditional novelty 6.0 of 10

    HalluField flags LLM hallucinations using a hand-weighted temperature-perturbation of token-level 'free energy' (negative log-likelihood) and Shannon entropy.

  2. Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?

    cs.AI 2025-06 conditional novelty 6.0 of 10

    Reasoning language models are systematically overconfident, deeper reasoning makes them more overconfident, and a two-stage introspective prompting method improves calibration for some models.

  3. Estimating LLM Uncertainty with Evidence

    cs.CL 2025-02 conditional novelty 6.0 of 10

    LogTokU splits token uncertainty into aleatoric and epistemic components from the top-K logits, enabling single-pass hallucination detection and uncertainty-guided decoding.

  4. keepitsimple at SemEval-2025 Task 3: LLM-Uncertainty based Approach for Multilingual Hallucination Span Detection

    cs.CL 2025-05 conditional novelty 4.0 of 10

    Hallucinated spans can be spotted by comparing many stochastic responses from the same model and flagging text where responses disagree, an entropy-based method that worked across 14 languages.

  5. 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.

Pith tools