arXiv cs.AI· Allen G. Roush, Minh Nhat Nguyen, Ravid Shwartz-Ziv, Judah Goldfeder, Sanjay Basu·· 56 分钟前精选AI 评分65
NeurIPS 2026 论文提出长文本生成本质是采样问题,top-nsigma 高温下表现突出
Long-Context Generation Is a Sampling Problem (When You Turn Up the Heat)
AI 导读
一项被 NeurIPS 2026 接收的研究测试了 29 个 1B 至 122B 开源模型与十项基准加一百万 token 检索,指出长文本生成退化主要取决于采样器如何随温度放大候选 token 池。
推荐理由
论文用 29 个开源模型和一百万 token 检索实验说明长文本退化主要源自采样器,读者可获得采样策略层面的可复用结论。
正文 · 原文
Abstract:Open-weight language models are widely observed to get worse the longer they generate. Often, attempts to fix this involve more training. At high temperature, The sampler, i.e. the rule that picks the next token out of the model's probabilities, decides whether long and agentic generation survives and/or thrives. We test 29 open-weight models from 1B to 122B parameters on ten established benchmarks plus needle retrieval out to one million tokens, covering SWE-bench Verified coding agents, long chain-of-thought reasoning, long-form writing, long structured output and long-context reading. Samplers that keep their pool of candidate tokens small and steady as temperature rises don't lose accuracy. Samplers that let in low-probability tokens fall apart. At temperature 2, coding agents running top-p, top-k or Top-H resolve 0 of 100 GitHub issues, while the same agents running top-nsigma resolve 46 to 62 and win every issue the two samplers disagree on, on three Qwen3.5 models. Over all benchmarks top-nsigma keeps a median 100% of its temperature-1 score where top-p keeps 26%. Counting how many tokens each sampler lets through explains why. In one Llama-3.1-8B story, going from temperature 1 to 2 grows top-p's pool from 4 tokens to 51,845 while top-nsigma stays at 3. Across 133 combinations of sampler setting and temperature, the typical pool size predicts judged quality (Spearman correlation of -0.77), and when we pick the pool at temperature 1 and only apply temperature afterwards, Top-H, min-p and p-less stop collapsing. At the default temperature of 1 most samplers perform about the same, We release all code and data to the public.
| Comments: | 10 pages, accepted to the 40th Conference on Neural Information Processing Systems (NeurIPS 2026). Track on Evaluations and Datasets |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.22148 [cs.AI] |
| (or arXiv:2611.22148v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22148 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Allen Roush [view email]
[v1]
Tue, 17 Nov 2026 03:30:03 UTC (457 KB)
来源:arXiv cs.AI · arxiv.org