Pith. sign in

REVIEW 1 cited by

Optimizing Temperature for Language Models with Multi-Sample Inference

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 2502.05234 v2 pith:ASXEDYXC submitted 2025-02-07 cs.LG cs.AIcs.CL

classification cs.LGcs.AIcs.CL
keywords temperaturemodelmulti-sampleperformanceaccuracyaggregationchallengedata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multi-sample aggregation strategies, such as majority voting and best-of-N sampling, are widely used in contemporary large language models (LLMs) to enhance predictive accuracy across various tasks. A key challenge in this process is temperature selection, which significantly impacts model performance. Existing approaches either rely on a fixed default temperature or require labeled validation data for tuning, which are often scarce and difficult to obtain. This paper addresses the challenge of automatically identifying the (near)-optimal temperature for different LLMs using multi-sample aggregation strategies, without relying on task-specific validation data. We provide a comprehensive analysis of temperature's role in performance optimization, considering variations in model architectures, datasets, task types, model sizes, and predictive accuracy. Furthermore, we propose a novel entropy-based metric for automated temperature optimization, which consistently outperforms fixed-temperature baselines. Additionally, we incorporate a stochastic process model to enhance interpretability, offering deeper insights into the relationship between temperature and model performance.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

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

  1. When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Hedged sampling, checklist-based one-pass selection (CHOPS), and cross-lingual MBR (X-MBR) improve multilingual LLM output quality when scaling from one to five samples.

Pith tools