Pith. sign in

REVIEW 2 cited by

The Stable Entropy Hypothesis and Entropy-Aware Decoding: An Analysis and Algorithm for Robust Natural Language Generation

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 2302.06784 v1 pith:ZWUJ4KWE submitted 2023-02-14 cs.CL

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

State-of-the-art language generation models can degenerate when applied to open-ended generation problems such as text completion, story generation, or dialog modeling. This degeneration usually shows up in the form of incoherence, lack of vocabulary diversity, and self-repetition or copying from the context. In this paper, we postulate that ``human-like'' generations usually lie in a narrow and nearly flat entropy band, and violation of these entropy bounds correlates with degenerate behavior. Our experiments show that this stable narrow entropy zone exists across models, tasks, and domains and confirm the hypothesis that violations of this zone correlate with degeneration. We then use this insight to propose an entropy-aware decoding algorithm that respects these entropy bounds resulting in less degenerate, more contextual, and "human-like" language generation in open-ended text generation settings.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

  1. APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    APCD reduces LLM hallucinations by expanding decoding paths adaptively when entropy signals uncertainty and by contrasting divergent paths to control their interaction.

  2. APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation

    cs.CL 2026-05 unverdicted novelty 5.0 of 10

    APCD adaptively branches LLM decoding paths based on token entropy and contrasts divergent paths to improve factual accuracy while preserving efficiency.

Pith tools