跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+979新增论文
+781其中 AI 相关
+119已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 02:56 — 2026-11-21 02:56(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

28,961 已收录论文24,030 AI 相关8,912 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 2 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.23112

Large-scale Neuron Community Discovery Reveals Neuron-Sparse Behaviors in Language Models

Igor Shilov, Thomas Fel, Tal Haklay, Lucius Bushnaq, Owen Lewis

原文摘要

What reusable units of computation can we discover within a language model's neurons? Prior work has shown that individual forward passes can often be sparsified post-hoc to small groups of neurons, but it has been unclear whether these groups form coherent computational entities reused across inputs. We introduce neuron community discovery, an unsupervised method for finding neuron groups that recur across prompts and are causally necessary and sufficient, within the layers they span, for common computations. The method combines gradient-based attribution, a graph connecting neurons that are repeatedly attributed together, and community detection. Applied to Llama-3.1-8B using ten million prompts, it discovers thousands of candidate communities. We evaluate them on held-out prompts through three causal tests: community necessity, sufficiency within a layer subset, and layer necessity. These tests identify groups whose removal disrupts predictions and whose retention preserves predictions despite ablating the remaining MLP neurons in the tested layers. Discovered communities support functions like grammatical agreement, token-probability calibration, fixed phrases, in-context copying, addition, and multiplication. With communities capped at 128 neurons across all layers, 10.3% of held-out prompts have at least one layer's contribution explained on a neuron-sparse basis. Coverage remains 8.7% when requiring at least four layers and 3.3% when requiring at least twelve. These results show that small groups of existing neurons can provide reusable computational components across prompts, and that such groups can be discovered at scale.

cs.LG · cs.CL

新论文 · v1arXiv:2611.07071

Shaping & Monitoring Models through their Internal Representations

Thomas Fel, Matthew Kowal, Matt Feiszli, Satchel Grant, Andrew Lee, Chris Earls, Fatih Dinc, Vasudev Shyam 等 26 位作者

原文摘要

We propose Mechanistic Shaping, a unified framework for shaping models through their internal representations. Mechanistic Shaping is applied during training so that models follow specifications (rules) about which concepts they express, measured via their outputs or internal representations (e.g., no harmful content), and also which concepts they rely on, i.e., what they use to make their decisions (e.g., not a candidate's gender when screening a résumé). Across multiple domains (vision, medical imaging, language), scales (up to 32B parameters), and training paradigms (classification, SFT, DPO, GRPO), we find that Mechanistic Shaping substantially reduces targeted behaviors while preserving task performance. Since training against a representation can also modify it, we ask whether shaped concepts remain monitorable, a question that depends on the class of monitors considered. We therefore introduce a hierarchy of such classes, which separates a concept that escapes one probe from a concept that is truly gone. We characterize three geometric mechanisms of circumvention: the concept can drift away from the monitor, be erased from the layer, or persist in higher-order statistics as a nonlinear encoding, which we explain through a product-code construction. Although other mechanisms may arise in different settings or at larger scales, these three account for all of our observations, and each can be detected by a matching monitor. In practice, we find that shaped concepts largely remain monitorable: refitted linear probes recover the concept in most settings, and the original probe remains reliable whenever gradients do not flow through it. Taken together, these results point to the potential of using interpretability as a tool for training, and call for a correspondingly rigorous science of interpretability-based training.

cs.LG · cs.AI