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

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 09:40 — 2026-11-16 09:40(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:2026-11-16 01:34最近发现新增版本:2026-11-14 15:09库内论文最新更新时间:2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 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 3 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.08639

Forcing a Letter Suppresses Refusal: Mechanistic Evidence from WMDP

Stepan Epifantsev, Anna Antipova, Oleg Chernikov, Leon Strelkov, Alexey Dontsov

原文摘要

Safety benchmarks for large language models (LLMs) commonly use multiple-choice question (MCQ) format. However, prior studies documented that MCQ format reduces refusal rates, which may significantly affect the safety behavior of the model. We provide a first mechanistic explanation of this effect on the Weapons of Mass Destruction Proxy (WMDP) dataset across two models - Llama-3.1-8B and Qwen3-8B. First, we use the tuned lens technique to show that when processing MCQ the model commits to an answer-letter token very quickly, which is in contrast to the gradual refusal build-up in open-ended formats. Additionally, we observe that activations on the MCQ format lie roughly 3x further from the refusal direction, compared with their open-ended counterparts. Moreover, ablating the attention heads that carry the MCQ format answer increases the refusal, which is a direct evidence that the MCQ answer-selection competes with refusal. These findings indicate that MCQ safety scores primarily measure knowledge capabilities and do not assess the safety-mechanisms.

cs.CL · cs.LG

版本更新 · v2arXiv:2602.14111

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Anton Korznikov, Andrey Galichin, Alexey Dontsov, Oleg Rogov, Ivan Oseledets, Elena Tutubalina

原文摘要

Sparse Autoencoders (SAEs) have emerged as a promising tool for interpreting neural networks by decomposing their activations into sparse sets of human-interpretable features. Recent work has introduced multiple SAE variants and successfully scaled them to frontier models. Despite much excitement, a growing number of negative results in downstream tasks casts doubt on whether SAEs recover meaningful features. To directly investigate this, we perform two complementary evaluations. On a synthetic setup with known ground-truth features, we demonstrate that SAEs recover only $9\%$ of true features despite achieving $71\%$ explained variance, showing that they fail at their core task even when reconstruction is strong. To evaluate SAEs on real activations, we introduce three baselines that constrain SAE feature directions or their activation patterns to random values. Through extensive experiments across multiple SAE architectures, we show that our baselines match fully-trained SAEs in interpretability (0.87 vs 0.90), sparse probing (0.69 vs 0.72), and causal editing (0.73 vs 0.72). Together, these results suggest that SAEs in their current state do not reliably decompose models' internal mechanisms.

cs.LG

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.17ACL Anthology · ACL 2026

Motivating Next-Gen Accelerators with Flexible N{:}M Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches

Shirin Alanova, Kristina Kazistova, Ekaterina Galaeva, Alina Kostromina, Vladimir Smirnov, Redko Dmitry, Alexey Dontsov, Maxim Zhelnin 等 10 位作者

原文摘要

The demand for efficient large language model inference has spurred interest in sparsification, yet current hardware support remains narrowly focused on 2:4 weight sparsity. In this work, we argue that activation sparsity despite being overlooked in hardware design offers a promising path for dynamic, input-adaptive compression with significant I/O and memory benefits. We present a comprehensive post-training study of N{:}M activation pruning across four LLMs (Llama2-7B-chat, Llama3.1-8B-Instruct, Qwen2.5-7B-Instruct, Gemma3-4B-Instruct), demonstrating that activation pruning consistently outperforms weight pruning at matched sparsity levels. We evaluate lightweight, plug-and-play error mitigation and selection strategies that require minimal or no calibration data across four sparsity patterns: 2:4, 4:8, 8:16, and 16:32. Among these, 16:32 approaches the performance of unstructured 50% sparsity and is is approximately 2.7\times better than 2:4, while 8:16 offers an optimal balance of accuracy and practicality. Our results provide evidence that next-generation accelerators should consider native support for N{:}M activation sparsity and can serve as a strong baseline for the future methods.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表