self-consistency 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
Official code for "Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration" (SOE, ACL 2026 Oral). A training-free, test-time scaling method that fixes reasoning collapse in LLM mathematical reasoning via orthogonal probing.
Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.
Awesome LLM Self-Consistency: a curated list of Self-consistency in Large Language Models
CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning
Zero-cost epistemic uncertainty quantification & hallucination detection for LLMs (90,000x faster than Semantic Entropy)
LLM reasoning: use draft agreement to route queries and allocate adaptive thinking budgets without training.
Black-box AI reliability certification via self-consistency sampling and conformal calibration
Capable, auditable coding that runs fully offline on a 16 GB machine. A verification-first layer (hard test execution, symbolic checking, agentic repair) that takes a local 7B to parity with its 671B teacher on verifiable tasks. MIT, pre-registered, reproducible.
KG-RAG + ToT + multi-agent LLMs for evidence-grounded QA with Neo4j and fine-tuning; reproducible medical case study & evaluation.
The official PyTorch implementation for the Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence
Object oriented package for solving self-consistent mean field theory of interacting lattice systems.
Prompt-engineering study on LLM math reasoning (GSM8K) and code generation (HumanEval): zero/few-shot, self-consistency, self-verification, and experiments on prompt quality, complexity, demonstrations, and diversity.
Perl implementation of Markov Chain for the course BIO331
An evaluation of prompting techniques (Zero-Shot CoT, Few-Shot, Self-Consistency) on the Mistral-7B model for mathematical reasoning. This project systematically benchmarks 7 distinct methods on the GSM8K dataset.
Code and results for consistency-gated self-correction in large language model reasoning.
GSM8K-Consistency is a benchmark database for analyzing the consistency of Arithmetic Reasoning on GSM8K.
JiuJiuBiao 九九表 — unified question answering over tables and databases: disambiguation (anchored rewrite), ReAct solver with self-consistency, self-criticism refinement; WTQ 0.82 / TabFact 0.97 / CLAMBSQL 0.68 / BIRD 0.67 on seeded samples
Fixed Point solver for generic functions
Tactical next-action + reasoning prediction on 348 football match contexts (Shipd Project Eris). 4-component ensemble with task-coupling: DeBERTa-v3-base / large, cross-encoder MCQ scorer, zero-shot NLI, and a three-pass Qwen3.5-35B-A3B-Int4 + Gemma-4-26B-A4B-it MoE fusion with PRM rerank. W&B-instrumented. Target combined ≥ 0.80
Router of 1.5–2B Qwen specialists + adaptive test-time compute that matches Phi-4-mini on held-out GSM8K, MMLU and HumanEval. A system, not a trained model.