pith. machine review for the scientific record. sign in

arxiv: 2203.11171 · v4 · submitted 2022-03-21 · 💻 cs.CL · cs.AI

Recognition: unknown

Self-Consistency Improves Chain of Thought Reasoning in Language Models

Aakanksha Chowdhery, Dale Schuurmans, Denny Zhou, Ed Chi, Jason Wei, Quoc Le, Sharan Narang, Xuezhi Wang

classification 💻 cs.CL cs.AI
keywords reasoningself-consistencychain-of-thoughtpromptinganswercomplexdecodinggreedy
0
0 comments X
read the original abstract

Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy decoding used in chain-of-thought prompting. It first samples a diverse set of reasoning paths instead of only taking the greedy one, and then selects the most consistent answer by marginalizing out the sampled reasoning paths. Self-consistency leverages the intuition that a complex reasoning problem typically admits multiple different ways of thinking leading to its unique correct answer. Our extensive empirical evaluation shows that self-consistency boosts the performance of chain-of-thought prompting with a striking margin on a range of popular arithmetic and commonsense reasoning benchmarks, including GSM8K (+17.9%), SVAMP (+11.0%), AQuA (+12.2%), StrategyQA (+6.4%) and ARC-challenge (+3.9%).

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 60 Pith papers

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

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

    cs.CL 2022-01 accept novelty 9.0

    Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.

  2. LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

    cs.CL 2026-05 conditional novelty 8.0

    AutoTTS discovers width-depth test-time scaling controllers through agentic search in a pre-collected trajectory environment, yielding better accuracy-cost tradeoffs than hand-designed baselines on math reasoning task...

  3. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

    cs.AI 2024-08 unverdicted novelty 8.0

    The AI Scientist framework enables LLMs to independently conduct the full scientific process from idea generation to paper writing and review, demonstrated across three ML subfields with papers costing under $15 each.

  4. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

    cs.CL 2023-10 conditional novelty 8.0

    DSPy compiles short declarative programs into LM pipelines that self-optimize and outperform both standard few-shot prompting and expert-written chains on math, retrieval, and QA tasks.

  5. Tree of Thoughts: Deliberate Problem Solving with Large Language Models

    cs.CL 2023-05 accept novelty 8.0

    Tree of Thoughts enables language models to solve complex planning tasks by generating, evaluating, and searching over coherent intermediate thoughts in a tree, raising Game of 24 success from 4% to 74% with GPT-4.

  6. Query-Conditioned Test-Time Self-Training for Large Language Models

    cs.CL 2026-05 unverdicted novelty 7.0

    QueST lets LLMs create query-conditioned problem-solution pairs at inference time and use them for parameter-efficient self-training, outperforming prior test-time baselines on math and science benchmarks.

  7. Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation

    cs.CL 2026-05 unverdicted novelty 7.0

    Evidence utility is defined as information gain on the model's output distribution, with ranking by gain on a latent helpfulness variable shown equivalent to answer-space utility under mild assumptions, enabling a tra...

  8. Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents

    cs.AI 2026-05 unverdicted novelty 7.0

    VeGAS improves MLLM-based embodied agents by sampling action ensembles and using a verifier trained on LLM-synthesized failure cases, yielding up to 36% relative gains on hard multi-object long-horizon tasks in Habita...

  9. Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking

    cs.CL 2026-05 unverdicted novelty 7.0

    BICR uses blind-image contrastive ranking on frozen LVLM hidden states to train a lightweight probe that penalizes confidence on blacked-out inputs, yielding top calibration and discrimination across five models and m...

  10. Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics

    cond-mat.stat-mech 2026-05 unverdicted novelty 7.0

    LLM multi-agent systems on lattices show bias-driven order-disorder crossovers instead of true phase transitions, with extracted effective couplings and fields serving as model-specific fingerprints.

  11. MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs

    cs.AI 2026-05 unverdicted novelty 7.0

    MAGE uses a four-subgraph co-evolutionary knowledge graph plus dual bandits to externalize and retrieve experience for stable self-evolution of frozen language-model agents, showing gains on nine diverse benchmarks.

  12. LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models

    cs.LG 2026-05 unverdicted novelty 7.0

    LEAD uses online adaptive mechanisms including Potential-Scaled Instability and symmetric efficiency rewards based on correct rollouts to achieve higher accuracy-efficiency scores with substantially shorter reasoning ...

  13. Beyond Accuracy: Evaluating Strategy Diversity in LLM Mathematical Reasoning

    cs.AI 2026-05 unverdicted novelty 7.0

    Frontier LLMs achieve 95-100% accuracy on AMC/AIME problems but recover far fewer distinct valid strategies than human references, while collectively generating 50 novel strategies.

  14. Re$^2$Math: Benchmarking Theorem Retrieval in Research-Level Mathematics

    cs.AI 2026-05 unverdicted novelty 7.0

    Re²Math is a new benchmark that evaluates AI models on retrieving and verifying the applicability of theorems from math literature to advance steps in partial proofs, accepting any sufficient theorem while controlling...

  15. Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck

    cs.LG 2026-05 unverdicted novelty 7.0

    CMIB uses a conditional multimodal information bottleneck to create reusable agent skills that separate verbalizable text content from predictive perceptual residuals, improving execution stability.

  16. LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

    cs.CL 2026-05 unverdicted novelty 7.0

    AutoTTS discovers superior test-time scaling strategies for LLMs via cheap controller synthesis in a pre-collected trajectory environment, outperforming manual baselines on math benchmarks with low discovery cost.

  17. CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation

    cs.CL 2026-05 unverdicted novelty 7.0

    CA-SQL achieves 51.72% execution accuracy on the challenging tier of the BIRD benchmark using GPT-4o-mini by scaling exploration breadth according to estimated task difficulty, evolutionary prompt seeding, and candida...

  18. Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models

    cs.CL 2026-05 unverdicted novelty 7.0

    Chain-based Distillation constructs a sequence of anchor models to enable efficient initialization of variable-sized SLMs through interpolation, with bridge distillation for cross-architecture transfer, yielding bette...

  19. Tracing Uncertainty in Language Model "Reasoning"

    cs.LG 2026-05 unverdicted novelty 7.0

    Uncertainty trace profiles from LM reasoning traces predict correct final answers with AUROC up to 0.807 and enable early error detection using only initial tokens.

  20. Regulating Branch Parallelism in LLM Serving

    cs.DC 2026-05 unverdicted novelty 7.0

    TAPER regulates LLM branch parallelism by admitting extra branches opportunistically when predicted externality fits slack, delivering 1.48-1.77x higher goodput than eager or fixed-cap baselines on Qwen3-32B while kee...

  21. Distributional Process Reward Models: Calibrated Prediction of Future Rewards via Conditional Optimal Transport

    cs.LG 2026-05 unverdicted novelty 7.0

    Conditional optimal transport calibrates PRMs by learning monotonic conditional quantile functions over success probabilities conditioned on hidden states, yielding improved calibration and downstream Best-of-N perfor...

  22. Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients

    cs.CL 2026-05 unverdicted novelty 7.0

    POPO uses bounded importance sampling on positive rollouts and a siamese policy network to achieve implicit negative gradients and stable optimization, matching or exceeding GRPO on math benchmarks such as 36.67% on A...

  23. Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key

    cs.AI 2026-05 unverdicted novelty 7.0

    RL training compute for logical reasoning follows a power law in proof depth whose exponent rises with logic expressiveness, and more expressive training yields larger gains on downstream benchmarks.

  24. Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key

    cs.AI 2026-05 unverdicted novelty 7.0

    RL training on more expressive logical tasks follows a steeper power-law scaling with reasoning depth and transfers more efficiently to math and reasoning benchmarks.

  25. Inference-Time Budget Control for LLM Search Agents

    cs.AI 2026-05 unverdicted novelty 7.0

    A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.

  26. Enhancing Agent Safety Judgment: Controlled Benchmark Rewriting and Analogical Reasoning for Deceptive Out-of-Distribution Scenarios

    cs.AI 2026-05 unverdicted novelty 7.0

    ROME generates deceptive safety benchmarks that degrade LLM agent judgment performance, while ARISE uses analogical retrieval to improve safety decisions at inference time without retraining.

  27. Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning

    cs.CL 2026-05 accept novelty 7.0

    Iterative LLM-driven search over reward functions, screened via GRPO on GSM8K, raises F1 from 0.609 baseline to 0.795 with ensembles on Llama-3.2-3B.

  28. Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning

    cs.CL 2026-05 unverdicted novelty 7.0

    Iterative search over reward functions with ranked feedback in GRPO training improves LLM math reasoning, achieving F1 of 0.795 on GSM8K versus 0.609 for baseline.

  29. TRIP-Evaluate: An Open Multimodal Benchmark for Evaluating Large Models in Transportation

    cs.CV 2026-04 accept novelty 7.0

    TRIP-Evaluate is a new open multimodal benchmark with 837 text, image, and point-cloud items organized by a role-task-knowledge taxonomy to evaluate large models on transportation workflows.

  30. Green Shielding: A User-Centric Approach Towards Trustworthy AI

    cs.CL 2026-04 unverdicted novelty 7.0

    Green Shielding introduces CUE criteria and the HCM-Dx benchmark to demonstrate that routine prompt variations systematically alter LLM diagnostic behavior along clinically relevant dimensions, producing Pareto-like t...

  31. Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees

    cs.LG 2026-04 unverdicted novelty 7.0

    Distinct Leaf Enumeration (DLE) replaces stochastic self-consistency sampling with deterministic traversal of a truncated decoding tree to enumerate distinct leaves, increasing coverage and reducing redundant computat...

  32. HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs

    cs.AI 2026-04 unverdicted novelty 7.0

    HiPO improves LLM reasoning performance by optimizing preferences separately on response segments rather than entire outputs.

  33. Learning When Not to Decide: A Framework for Overcoming Factual Presumptuousness in AI Adjudication

    cs.AI 2026-04 unverdicted novelty 7.0

    A new structured prompting method (SPEC) helps AI detect insufficient evidence in adjudication tasks and defer decisions appropriately, reaching 89% accuracy on a benchmark varying information completeness from Colora...

  34. Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents

    cs.AI 2026-04 unverdicted novelty 7.0

    Long-horizon enterprise AI agents' decisions decompose into four measurable axes, with benchmark experiments on six memory architectures revealing distinct weaknesses and reversing a pre-registered prediction on summa...

  35. Structural Verification for Reliable EDA Code Generation without Tool-in-the-Loop Debugging

    cs.SE 2026-04 unverdicted novelty 7.0

    Structural dependency graphs and staged pre-execution verification raise LLM-based EDA code pass rates to 82.5% (single-step) and 70-84% (multi-step) while halving tool calls by catching dependency violations before runtime.

  36. AI scientists produce results without reasoning scientifically

    cs.AI 2026-04 conditional novelty 7.0

    LLM agents execute scientific tasks but fail to follow core scientific reasoning norms such as evidence consideration and belief revision based on refutations.

  37. Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning

    cs.CL 2026-04 unverdicted novelty 7.0

    CoT-PoT ensembling achieves self-consistency accuracy in LLMs with only two samples for 78.6% of tasks, reducing computation by 9.3x compared to standard methods.

  38. Clover: A Neural-Symbolic Agentic Harness with Stochastic Tree-of-Thoughts for Verified RTL Repair

    cs.AR 2026-04 unverdicted novelty 7.0

    Clover fixes 96.8% of bugs on an RTL-repair benchmark using stochastic tree-of-thoughts and neural-symbolic agents, outperforming traditional and LLM baselines by 94% and 63% respectively with 87.5% pass@1.

  39. Evaluating Tool-Using Language Agents: Judge Reliability, Propagation Cascades, and Runtime Mitigation in AgentProp-Bench

    cs.AI 2026-04 conditional novelty 7.0

    AgentProp-Bench shows substring judging agrees with humans at kappa=0.049, LLM ensemble at 0.432, bad-parameter injection propagates with ~0.62 probability, rejection and recovery are independent, and a runtime fix cu...

  40. SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees

    cs.LG 2026-04 unverdicted novelty 7.0

    SAT trains multi-LLM teams with sequential block updates to deliver monotonic gains and plug-and-play model swaps that provably improve performance bounds.

  41. TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens

    cs.CV 2026-04 unverdicted novelty 7.0

    TokenGS uses learnable Gaussian tokens in an encoder-decoder architecture to regress 3D means directly, achieving SOTA feed-forward reconstruction on static and dynamic scenes with better robustness.

  42. Feedback-Driven Execution for LLM-Based Binary Analysis

    cs.CR 2026-04 unverdicted novelty 7.0

    FORGE uses a reasoning-action-observation loop and Dynamic Forest of Agents to perform scalable LLM-based binary analysis, finding 1,274 vulnerabilities across 591 of 3,457 real-world firmware binaries at 72.3% precis...

  43. Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap

    cs.SE 2026-04 unverdicted novelty 7.0

    Atropos uses GCN on inference graphs for early failure prediction and hotswaps to larger LLMs, achieving 74% of large-model performance at 24% cost.

  44. SAGER: Self-Evolving User Policy Skills for Recommendation Agent

    cs.IR 2026-04 unverdicted novelty 7.0

    SAGER equips LLM recommendation agents with per-user evolving policy skills via two-representation architecture, contrastive CoT diagnosis, and skill-augmented listwise reasoning, yielding SOTA gains orthogonal to mem...

  45. Structural Anchors and Reasoning Fragility:Understanding CoT Robustness in LLM4Code

    cs.SE 2026-04 unverdicted novelty 7.0

    CoT prompting in LLM4Code shows mixed robustness that depends on model family, task structure, and perturbations destabilizing structural anchors, leading to trajectory deformations like lengthening, branching, and si...

  46. Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation

    cs.SE 2026-04 unverdicted novelty 7.0

    LLM deobfuscation of binaries to pseudocode depends more on reasoning ability and task-specific fine-tuning than on model size, with reasoning models showing robustness across ISAs and obfuscation levels on the new Bi...

  47. Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models

    cs.CL 2026-04 unverdicted novelty 7.0

    PPT-Bench measures how LLMs change answers under epistemic, value, authority, and identity pressures at baseline, single-turn, and multi-turn levels, finding separable inconsistency patterns across five models.

  48. iTAG: Inverse Design for Natural Text Generation with Accurate Causal Graph Annotations

    cs.CL 2026-04 unverdicted novelty 7.0

    iTAG generates natural text paired with accurate causal graph annotations by framing concept assignment as an inverse problem and refining selections via chain-of-thought reasoning until the text's relations align wit...

  49. Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents

    cs.AI 2026-04 unverdicted novelty 7.0

    PTR framework profiles a workflow upfront then executes it deterministically with bounded verification and repair, limiting LM calls to 2-3 while outperforming ReAct in 16 of 24 tested configurations.

  50. User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendation

    cs.IR 2026-04 unverdicted novelty 7.0

    SMTPO uses multi-task SFT to improve simulator feedback quality and RL with fine-grained rewards to optimize multi-turn preference reasoning in LLM-based conversational recommendation.

  51. Evaluating the Environmental Impact of using SLMs and Prompt Engineering for Code Generation

    cs.SE 2026-04 unverdicted novelty 7.0

    Chain-of-Thought prompting balances high accuracy with low energy use in small language models for code generation, while multi-sampling strategies add high energy costs for small accuracy gains.

  52. PLUME: Latent Reasoning Based Universal Multimodal Embedding

    cs.CV 2026-04 unverdicted novelty 7.0

    PLUME uses latent-state autoregressive rollouts and a progressive training curriculum to deliver efficient reasoning for universal multimodal embeddings without generating explicit rationales.

  53. Let's Verify Step by Step

    cs.LG 2023-05 accept novelty 7.0

    Process supervision significantly outperforms outcome supervision for training models on the MATH dataset, achieving 78% accuracy on a representative test subset with active learning and a released 800k step-label dataset.

  54. Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

    cs.CV 2023-03 accept novelty 7.0

    Visual ChatGPT integrates visual foundation models with ChatGPT via prompts to enable multi-step image understanding, generation, and editing in conversational interactions.

  55. RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning

    cs.CL 2026-05 unverdicted novelty 6.0

    RTLC prompting lifts Claude 3.7 Sonnet pairwise accuracy on 350 hard JudgeBench items from 64.6% to 78.6% via a Research-Teach-Critique scaffold that beats self-consistency.

  56. STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes

    cs.CL 2026-05 unverdicted novelty 6.0

    STOP uses structured on-policy analysis to prune long reasoning traces to their earliest correct node, cutting token usage 19-42% with little accuracy loss on math benchmarks.

  57. Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration

    cs.CV 2026-05 unverdicted novelty 6.0

    A training-free attention-guided debiasing framework mitigates position bias in MLLM multi-image retrieval by exploiting the observed mismatch between biased logits and aligned attention maps, yielding over 40% accura...

  58. Training-Free Cultural Alignment of Large Language Models via Persona Disagreement

    cs.CL 2026-05 unverdicted novelty 6.0

    DISCA uses disagreement among WVS-grounded persona panels to apply loss-averse logit corrections that reduce cultural misalignment by 10-24% on MultiTP for models 3.8B and larger, without weight changes.

  59. What should post-training optimize? A test-time scaling law perspective

    cs.LG 2026-05 unverdicted novelty 6.0

    Tail-extrapolated estimators approximate best-of-N policy gradients from limited training rollouts by leveraging upper-tail reward statistics under structural assumptions.

  60. Active Testing of Large Language Models via Approximate Neyman Allocation

    cs.AI 2026-05 unverdicted novelty 6.0

    Active testing via surrogate semantic entropy stratification and approximate Neyman allocation reduces MSE by up to 28% versus uniform sampling and saves about 23% of the labeling budget on language and multimodal benchmarks.