Research map / Large language models / Reasoning and chain of thought
Task-and-Model-Aware Fractal-Consistency for Efficient LLM Reasoning
Ziqiu Luo, Jianmin Liu, Yukai Miao, Li Chen, Dan Li
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a task-and-model-aware, fractal-style consistency method for LLM reasoning that aims to reduce the compute cost of self-consistency by evaluating consistency at finer granularity and using adaptive rather than static stopping/aggregation.
Problem
Self-consistency methods aggregate many stochastic LLM samples to improve answer correctness, but they are computationally expensive because they judge output consistency monolithically and use static sampling/aggregation settings.
Approach
Evaluates consistency fractally, so partially correct answers across samples can be combined efficiently, and adapts the consistency procedure to the task and model rather than using static settings.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Fractal-Consistency and ASCC (TMAFC) over Adaptive-Consistency | GPT-4 sampling · structured tasks (NER) | sampling cost: 36.81 -> 16.44 | Improved |
| add Fractal-Consistency and ASCC (TMAFC) over Adaptive-Consistency | GPT-4 sampling · EE (structured) | accuracy: 41.8% -> 43.6% | Improved |
| add component-wise Fractal-Consistency (remove ASCC) (ablation) | TMAFC · NER (structured) | sampling cost: 36.81 (AC) -> 19.32 (w/o ASCC) | Improved |
| add ASCC on top of Fractal-Consistency (ablation) | TMAFC · NER (structured) | sampling cost: 19.32 -> 16.44 | Improved |
| add ASCC on top of Fractal-Consistency (ablation) | TMAFC · EE (structured) | accuracy: 43.7% -> 43.6% | No clear effect |
| add Fractal-Consistency on top of ASCC (w/o FC variant) (ablation) | TMAFC · Math-Reasoning (Hard) | accuracy: 68.1% -> 68.5% | Improved |
| add Fractal-Consistency on top of ASCC (w/o FC variant) (ablation) | TMAFC · Mathematical Reasoning (unstructured) | sampling cost: 28.52 -> 21.24 | Improved |
| adaptive prior (alpha0, beta0) instead of fixed (1,1) | Adaptive-Consistency · hybrid tasks, GPT-4 | sampling cost: 8.61 -> 4.14 | Improved |
| adaptive prior on weak model on hard questions | Adaptive-Consistency · hybrid tasks, Llama3-8B-Instruct | sampling cost: 24.66 -> 22.4 (-9.1%) | Improved |
| inject synthetic anchor errors (0% to 50%) (ablation) | TMAFC · unstructured tasks | accuracy and sampling cost | Hurt |
| replace LLM-based difficulty classifier with XGBoost or DistilBERT (ablation) | ASCC · cross-domain 300 questions | end-to-end performance | Hurt |
| vary classifier accuracy 65% to 90% via noise injection (ablation) | ASCC · cross-domain 300 questions | accuracy and cost | No clear effect |
Limitations
- Only the abstract was available; experimental details, models and benchmarks are unknown.
Experimental setup
Baselines: self-consistency
Builds on: self-consistency
Closest papers by meaning
- A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning (NeurIPS 2025 · similarity 0.92)
- Representation Consistency for Accurate and Coherent LLM Answer Aggregation (NeurIPS 2025 · similarity 0.92)
- Optimal Self-Consistency for Efficient Reasoning with Large Language Models (ICML 2026 · similarity 0.90)
- Latent Self-Consistency for Reliable Majority-Set Selection in Short- and Long-Answer Reasoning (AAAI 2026 · similarity 0.90)
- CITE: Anytime Valid Statistical Inference in LLM Self-Consistency (NeurIPS 2026 · similarity 0.88)
- Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs (ICLR 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
