Tag: Interpretability
All the articles with the tag "Interpretability".
-
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
Published: at 10:59 AM
85.36 🤔This paper introduces a taxonomy of language model memorization into recitation, reconstruction, and recollection, demonstrating through experiments with Pythia models that different factors influence each category, with a taxonomy-based predictive model outperforming baselines in predicting memorization likelihood.
-
RM-R1: Reward Modeling as Reasoning
Published: at 12:11 AM 85.26 🤔本文提出RM-R1，一种通过将奖励建模转化为推理任务并结合蒸馏和强化学习训练的推理奖励模型（REASRMS），在多个基准测试上取得了最先进性能，同时显著提升了可解释性。
-
Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking
Published: at 11:15 PM 83.31 🤔本文提出InteRank方法，通过知识蒸馏和强化学习训练一个3B参数小型语言模型，在推理密集型文档重排序任务中生成解释并实现与70B+参数模型相当的性能，在BRIGHT基准上位列第三。
-
From Attention to Atoms: Spectral Dictionary Learning for Fast, Interpretable Language Models
Published: at 04:33 PM 75.71 🤔本文提出光谱字典生成模型（SDGM），通过学习全局傅里叶字典和 token 混合系数替换自注意力机制，实现 O(KL) 复杂度的高效语言建模，并在基准数据集上取得竞争性 perplexity 和显著的资源节省。
-
Racing Thoughts: Explaining Contextualization Errors in Large Language Models
Published: at 12:18 AM 74.82 🤔本文提出‘LLM Race Conditions Hypothesis’解释大型语言模型的上下文化错误，通过机械可解释性技术验证了关键窗口和上下文化顺序对模型性能的影响，并探索了推理时干预措施来缓解问题。