Pith. sign in

REVIEW 6 cited by

EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling

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 2403.14541 v2 pith:W2LSPWYJ submitted 2024-03-21 cs.CL

EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling

classification cs.CL
keywords generationtemperaturelanguageperformancesamplingacrossdifferentdiversity
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recently, Large Language Models (LLMs) have demonstrated outstanding performance across a wide range of downstream language tasks. Temperature sampling is a commonly used decoding strategy for LLMs' generation process. However, a fixed temperature parameter is used in most cases, which may not always be an optimal choice for balancing generation quality and diversity. In this paper, we propose an effective Entropy-based Dynamic Temperature (EDT) Sampling method, to achieve a more balanced performance in terms of both generation quality and diversity by dynamically selecting the temperature parameter. Additionally, we also show model performance and comprehensive analyses for 4 different generation benchmarks. Our experiments show that EDT significantly outperforms the existing strategies across different tasks.

discussion (0)

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

Forward citations

Cited by 6 Pith papers

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

  1. Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement

    cs.CL 2026-05 unverdicted novelty 7.0

    Autoregressive transformers exhibit measurable cognitive fatigue during extended generation, quantified by the Fatigue Index that predicts degradation (AUROC 0.95) and repetition (rho 0.94).

  2. Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation

    cs.LG 2026-05 unverdicted novelty 7.0

    Energy-navigated trajectory shaping during training produces 8-step discrete flow matching students that achieve 32% lower perplexity than 1024-step teachers on 170M language models with unchanged inference cost.

  3. Improving Sample Diversity in Autoregressive Text-to-Image Generation via Cluster Truncation

    cs.CV 2026-07 conditional novelty 6.0

    p-less cluster decoding, which truncates and samples over K-means clusters of visual tokens rather than individual tokens, yields higher per-prompt sample diversity than default or dynamic-temperature baselines on mos...

  4. Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization

    cs.LG 2026-06 unverdicted novelty 6.0

    Unsupervised rewards combining model uncertainty and semantic consistency allow protein language models to self-steer via SRO and BRO algorithms, outperforming DPO and KTO on out-of-distribution prompts while approach...

  5. Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation

    cs.CL 2026-04 unverdicted novelty 5.0

    Residual-stream noise injection raises narrative diversity in Arabic educational stories while preserving reading-grade level, outperforming high-temperature sampling across five 7-9B models.

  6. Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning

    cs.CL 2026-05 unverdicted novelty 4.0

    TS-OPSD internalizes temperature via on-policy self-distillation to reheat entropy-collapsed RL policies in LLMs, providing stronger initialization for further training than continued RL or rollout temperature adjustment.