Pith. sign in

REVIEW 11 cited by

Efficient Test-Time Scaling via Self-Calibration

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 2503.00031 v1 pith:I7WRJX3T submitted 2025-02-25 cs.LG cs.AIcs.CL

classification cs.LGcs.AIcs.CL
keywords confidenceresponsestest-timebest-of-nconfidence-basedllmssamplingscaling
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Increasing test-time computation is a straightforward approach to enhancing the quality of responses in Large Language Models (LLMs). While Best-of-N sampling and Self-Consistency with majority voting are simple and effective, they require a fixed number of sampling responses for each query, regardless of its complexity. This could result in wasted computation for simpler questions and insufficient exploration for more challenging ones. In this work, we argue that model confidence of responses can be used for improving the efficiency of test-time scaling. Unfortunately, LLMs are known to be overconfident and provide unreliable confidence estimation. To address this limitation, we introduce Self-Calibration by distilling Self-Consistency-derived confidence into the model itself. This enables reliable confidence estimation at test time with one forward pass. We then design confidence-based efficient test-time scaling methods to handle queries of various difficulty, such as Early-Stopping for Best-of-N and Self-Consistency with calibrated confidence. Experiments on three LLMs across six datasets demonstrate the effectiveness of our approach. Specifically, applying confidence-based Early Stopping to Best-of-N improves MathQA accuracy from 81.0 to 83.6 with a sample budget of 16 responses, indicating the efficacy of confidence-based sampling strategy at inference time.

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

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

  1. Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

    cs.CL 2025-09 conditional novelty 6.0 of 10

    Parallel-R1 uses SFT cold-start on easy math plus GRPO on hard math to instill parallel thinking in Qwen3-4B, reporting 8.4% average accuracy gains and a 42.9% AIME25 gain from a parallel-exploration scaffold.

  2. AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control

    cs.CL 2025-06 conditional novelty 6.0 of 10

    AALC, an accuracy-aware length reward, reduces reasoning-model response length by over 50% on math benchmarks while preserving or improving accuracy.

  3. How Far Are We from Optimal Reasoning Efficiency?

    cs.CL 2025-06 conditional novelty 6.0 of 10

    The authors define a reasoning efficiency frontier and a gap metric (REG), then train models with REO-RL to shrink the gap by at least 50% with only small accuracy losses.

  4. AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

    cs.CL 2025-06 conditional novelty 6.0 of 10

    AdaDecode speeds up LLM generation by predicting tokens at early layers when confidence is high, running the skipped layers in parallel, and verifying the output exactly matches standard decoding.

  5. POSS: Position Specialist Generates Better Draft for Speculative Decoding

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Using position-specialized draft layers instead of one single draft model improves later-token acceptance in speculative decoding, yielding modest speedups on Llama-3-8B and Llama-2-13B.

  6. Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Post-training alignment on synthetic graph data yields statistically significant gains on some real-world implicit-graph tasks, but gains are inconsistent and multi-step reasoning remains fragile.

  7. CGES: Confidence-Guided Early Stopping for Efficient and Accurate Self-Consistency

    cs.CL 2025-11 conditional novelty 5.0 of 10

    Confidence-Guided Early Stopping stops querying an LLM once one candidate answer accumulates enough Bayesian posterior mass, cutting average calls from 16 to 4.9 on five reasoning benchmarks with negligible average ac...

  8. Confidence-Weighted Token Set Cover for Early Hypothesis Pruning in Self-Consistency

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    A weighted set cover algorithm prunes intermediate hypotheses during self-consistency, cutting token use by 10 to 35 percent across five LLMs on three math benchmarks while keeping accuracy.

  9. Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs

    cs.AI 2025-07 conditional novelty 5.0 of 10

    The survey's L1/L2 taxonomy and benchmark show that current reasoning models waste compute on easy problems and underthink hard ones, motivating more adaptive inference.

  10. Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning

    cs.CL 2025-06 conditional novelty 5.0 of 10

    ADAPT, a diversity-aware prefix fine-tuning method, improves best-of-N sampling efficiency for a 1.5B reasoning model, reaching 80% accuracy at N=32 versus N=256 for the baseline.

  11. Interpretable Adaptive Sampling for LLM Test-Time Scaling

    cs.AI 2026-08 reject novelty 4.0 of 10

    A fuzzy controller that allocates a per-prompt sampling budget keeps LLM accuracy near a fixed full-budget baseline while reducing the average number of candidate answers on some datasets.

Pith tools