Pith. sign in

REVIEW 12 cited by

Trusting Your Evidence: Hallucinate Less with Context-aware Decoding

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 2305.14739 v1 pith:PCJG4TUC submitted 2023-05-24 cs.CL

Trusting Your Evidence: Hallucinate Less with Context-aware Decoding

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

Language models (LMs) often struggle to pay enough attention to the input context, and generate texts that are unfaithful or contain hallucinations. To mitigate this issue, we present context-aware decoding (CAD), which follows a contrastive output distribution that amplifies the difference between the output probabilities when a model is used with and without context. Our experiments show that CAD, without additional training, significantly improves the faithfulness of different LM families, including OPT, GPT, LLaMA and FLAN-T5 for summarization tasks (e.g., 14.3% gain for LLaMA in factuality metrics). Furthermore, CAD is particularly effective in overriding a model's prior knowledge when it contradicts the provided context, leading to substantial improvements in tasks where resolving the knowledge conflict is essential.

discussion (0)

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

Forward citations

Cited by 12 Pith papers

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

  1. Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing

    cs.LG 2026-05 unverdicted novelty 7.0

    Contrastive Decoding Diffing recovers exact implanted facts from finetuned LLMs via logit-space differences between finetuned and base models, outperforming white-box baselines with less access.

  2. Hallucination is Inevitable: An Innate Limitation of Large Language Models

    cs.CL 2024-01 conditional novelty 7.0

    Hallucinations are inevitable in LLMs because they cannot learn all computable functions according to learning theory.

  3. Answer Engineering: Local Trajectory Editing for Protocol-Constrained Decision Making in Large Language Models

    cs.AI 2026-06 unverdicted novelty 6.0

    Answer Engineering uses local trajectory editing during autoregressive generation to raise protocol compliance on a clinical SSNHL benchmark from 25.1% to 83.5% and balanced accuracy from 42.0% to 80.7%.

  4. Trust or Abstain? A Self-Aware RAG Approach

    cs.IR 2026-05 unverdicted novelty 6.0

    SABER combines self-prior with multi-trace PK and CK reasoning representations to estimate reliability beliefs and drive trust-or-abstain decisions in knowledge-conflict RAG, improving accuracy over baselines.

  5. No-Worse Context-Aware Decoding: Preventing Neutral Regression in Context-Conditioned Generation

    cs.CL 2026-04 unverdicted novelty 6.0

    NWCAD uses a two-stream setup with a two-stage gate to prevent accuracy drops on baseline-correct items under non-informative contexts while retaining gains from helpful contexts.

  6. DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

    cs.CL 2023-09 conditional novelty 6.0

    DoLa reduces hallucinations in LLMs by contrasting logits from later versus earlier layers during decoding, improving truthfulness on TruthfulQA by 12-17 absolute points without fine-tuning or retrieval.

  7. HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs

    cs.CL 2026-05 unverdicted novelty 5.0

    HalluScan benchmark tests hallucination detectors on LLMs, identifies NLI Verification as top performer with 0.88 AUROC, and introduces HalluScore (r=0.41 with humans) plus a routing method for 2x cost savings.

  8. 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.

  9. HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs

    cs.CL 2026-05 unverdicted novelty 4.0

    HalluScan benchmark evaluates hallucination detection in LLMs, reporting NLI Verification at AUROC 0.88 and introducing HalluScore (r=0.41 with humans) plus Adaptive Detection Routing for 2x cost savings.

  10. Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)

    cs.LG 2026-04 unverdicted novelty 4.0

    HUMBR reduces LLM hallucinations in enterprise workflows by using a hybrid semantic-lexical utility within minimum Bayes risk decoding to identify consensus outputs, with derived error bounds and reported outperforman...

  11. Inteligencia Artificial jur\'idica y el desaf\'io de la veracidad: an\'alisis de alucinaciones, optimizaci\'on de RAG y principios para una integraci\'on responsable

    cs.AI 2025-09 conditional novelty 4.0

    Legal AI hallucination persists in commercial RAG tools (17-34%+ of queries), so the report argues the fix is consultative, source-citing system design plus mandatory human oversight, not better generative models.

  12. Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models

    cs.CL 2023-09 unverdicted novelty 4.0

    A literature survey that taxonomizes hallucination phenomena in LLMs, reviews evaluation benchmarks, and analyzes approaches for their detection, explanation, and mitigation.