arXiv：cs.CL· Javier Mar\'in·· 3 小时前AI 评分37
因实验未实现验收标准，APE 选择性微调论文被作者撤回
APE: Selective Fine-tuning with Acceptance Criteria for Language Model Adaptation
AI 导读
作者 Javier Marin 撤回 arXiv 论文 APE（Adjacent Possible Exploration），原因是第 3 节实验（Table 3、Figure 2）未实现第 2 节所述的验收标准，且第 3.2 节人工评估无效。
正文
This paper has been withdrawn by Javier Marin
No PDF available, click to view other formats
Abstract:We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization principles, APE evaluates multiple candidate parameter updates through fine-tuning on small data subsets and accepts only those exceeding a performance threshold. Unlike standard fine-tuning that follows single gradient directions, APE implements a filtered selection process that prevents destabilizing parameter changes while enabling systematic improvement. Our method achieves 33.9\% BLEU improvement and 36.2\% perplexity reduction on news summarization tasks while using minimal computational resources. The approach provides a practical framework for controlled model adaptation that balances performance gains with representational stability.
| Comments: | Withdrawn by the author. The experiments reported in Section 3 (Table 3, Figure 2) do not implement the acceptance criterion described in Section 2, and the human evaluation in Section 3.2 is not valid. The reported results and conclusions should be disregarded |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2505.19912 [cs.CL] |
| (or arXiv:2505.19912v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2505.19912 arXiv-issued DOI via DataCite |
Submission history
From: Javier Marin [view email]
[v1]
Mon, 26 May 2025 12:39:24 UTC (34 KB)
[v2]
Mon, 9 Jun 2025 10:21:49 UTC (26 KB)
[v3]
Tue, 6 Oct 2026 20:25:14 UTC (1 KB) (withdrawn)
来源：arXiv：cs.CL · arxiv.org