arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.26183cs.CL
收藏

相似-距离-数量语言模型

Similarity-Distance-Magnitude Language Models

Reexpress AI

Allen Schmaltz

摘要:

我们介绍了相似性-距离-幅度(SDM)语言模型(LM),这是序列预测模型微调,以最大限度地提高比例的代在良好的校准,高概率区域划分的最后一层SDM激活层用于二进制分类的预防以下。我们证明,现有的预训练仅解码器的Transformer LM可以通过监督微调轻松转换为SDM LM,在训练期间使用最终层SDM激活层来估计对比输入编码方案上监督下一个令牌丢失的基础变化,并在训练期间在线生成额外的硬负示例。这导致弃权减少(即,提高统计效率)。

英文摘要:

We introduce Similarity-Distance-Magnitude (SDM) language models (LMs), which are sequence prediction models fine-tuned to maximize the proportion of generations in the well-calibrated, high-probability region partitioned by a final-layer SDM activation layer used for binary classification of instruction-following. We demonstrate that existing pre-trained decoder-only Transformer LMs can be readily converted into SDM LMs via supervised fine-tuning, using the final-layer SDM activation layer during training to estimate a change-of-base for a supervised next-token loss over a contrastive input encoding scheme, with additional hard negative examples generated online during training. This results in reduced abstentions (i.e., improved statistical efficiency) compared to strong supervised baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑