Pith. sign in

REVIEW 12 cited by

Contrastive Decoding Improves Reasoning in Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2309.09117 v2 pith:IHWICRQN submitted 2023-09-17 cs.CL cs.AI

Sean O'Brien , Mike Lewis This is my paper · ORCID
classification cs.CLcs.AI
keywords decodingcontrastivereasoninggenerationmodelstaskstextbenchmark
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We demonstrate that Contrastive Decoding -- a simple, computationally light, and training-free text generation method proposed by Li et al 2022 -- achieves large out-of-the-box improvements over greedy decoding on a variety of reasoning tasks. Originally shown to improve the perceived quality of long-form text generation, Contrastive Decoding searches for strings that maximize a weighted difference in likelihood between strong and weak models. We show that Contrastive Decoding leads LLaMA-65B to outperform LLaMA 2, GPT-3.5 and PaLM 2-L on the HellaSwag commonsense reasoning benchmark, and to outperform LLaMA 2, GPT-3.5 and PaLM-540B on the GSM8K math word reasoning benchmark, in addition to improvements on a collection of other tasks. Analysis suggests that Contrastive Decoding improves over existing methods by preventing some abstract reasoning errors, as well as by avoiding simpler modes such as copying sections of the input during chain-of-thought. Overall, Contrastive Decoding outperforms nucleus sampling for long-form generation and greedy decoding for reasoning tasks, making it a powerful general purpose method for generating text from language models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

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

  1. Improving LLMs via Validator-to-Generator Alignment

    cs.CL 2026-07 conditional novelty 7.0 of 10

    Frequency-corrected rank alignment of an LLM generator to its own validator improves generator AUROC and G-V Pearson correlation by up to 27 points while preserving validator quality.

  2. Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL

    cs.AI 2026-07 conditional novelty 6.0 of 10

    PRISM trains one positive policy per reward plus one global negative policy and merges their token logits, improving multi-reward RL for LLMs with inference-time controllability.

  3. Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Lossy speculative-decoding verification splits into truncation-based and collaborative methods; truncation-based methods underperform their matched baselines, and capping draft overshoot preserves quality.

  4. CROP: Circuit Retrieval and Optimization with Parameter Guidance using LLMs

    cs.LG 2025-07 conditional novelty 6.0 of 10

    LLM-based retrieval-augmented tuning of EDA flow parameters found a 9.9% lower-power configuration on one industrial core than classical optimizers.

  5. Dual Debiasing for Noisy In-Context Learning for Text Generation

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A dual-debiasing method normalizes perplexity by the model's prior knowledge and a query-specific baseline, detecting noisy ICL demonstrations even at 80% noise.

  6. DecoRTL: A Run-time Decoding Framework for RTL Code Generation with LLMs

    cs.PL 2025-07 conditional novelty 5.0 of 10

    DecoRTL combines token-class-aware temperature adjustment with contrastive top-K reranking to improve synthesizability and functional correctness of LLM-generated Verilog.

  7. EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding

    cs.CL 2025-06 conditional novelty 5.0 of 10

    EpiCoDe builds an extrapolated checkpoint from early and late finetuned models, then subtracts the late model's logits from the extrapolated model's logits during decoding to boost accuracy.

  8. Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs

    cs.CL 2025-06 reject novelty 5.0 of 10

    ASTS extends locally typical sampling with semantic scoring and dynamic thresholds, reporting improved perplexity, MAUVE, and diversity on story and summarization tasks.

  9. RAST: Reasoning Activation in LLMs via Small-model Transfer

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Injecting the logit gap between a small RL-trained model and its base into a larger base model at decoding time improves reasoning accuracy on math and code benchmarks, sometimes matching or exceeding RL training of t...

  10. Exploring and Mitigating Fawning Hallucinations in Large Language Models

    cs.CL 2025-08 conditional novelty 4.0 of 10

    A contrastive decoding method that contrasts a misleading prompt against a neutral rewrite reduces fawning hallucinations in LLMs, though most of the gain comes from the neutral prompt itself.

  11. UCD: Unlearning in LLMs via Contrastive Decoding

    cs.CL 2025-06 conditional novelty 4.0 of 10

    UCD steers an LLM away from forget-set content at inference time by mixing in the difference between forget-tuned and retain-tuned small models.

  12. Large Language Models for Planning: A Comprehensive and Systematic Survey

    cs.AI 2025-05 conditional novelty 3.0 of 10

    A structured survey of LLM planning methods, benchmarks, and interpretability work, organized around a three-way taxonomy.

Pith tools