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

+1284新增论文
+1011其中 AI 相关
+150已有论文修订
+97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 10:50各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 11:07 — 2026-11-20 11:07(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 10:50库内论文最新更新时间:2026-11-19 12:39

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。

28,155 已收录论文23,386 AI 相关8,624 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 2026-11-20 08:46(北京时间)
版本更新 · v3arXiv:2605.15491

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs

Vincent-Daniel Yun, Junhyuk Jo, Sai Praneeth Karimireddy, Sunwoo Lee

原文摘要

Layer pruning removes entire Transformer decoder blocks from large language models, but introduces a mismatch between the hidden state received by the next surviving layer and the distribution it was trained to process, leading to significant performance degradation. We propose Ghosted Layers, a training-free recovery module that addresses this issue by solving a boundary activation alignment problem. Our method derives a closed-form optimal linear operator from a small calibration set to reconstruct the activation discrepancy introduced by the pruned layers. We show that this solution corresponds to the unconstrained optimum of the alignment objective, whereas LinearPatch is restricted to a fixed basis symmetric operator family. Across multiple LLM backbones, pruning strategies, and pruning depths, Ghosted Layers outperforms prior training-free recovery methods in accuracy and perplexity in most settings while preserving the efficiency benefits of layer pruning.

cs.LG · cs.AI · cs.PF

版本更新 · v2arXiv:2609.38379

Aligned Data Can Induce Misalignment via Context Confusion

Yavuz Bakman, Duygu Nur Yaldiz, Baris Askin, Swastik Roy, Morteza Ziyadi, Salman Avestimehr, Sai Praneeth Karimireddy

原文摘要

Large language models are frequently updated for various use cases, where filtering out misaligned training samples is a common practice for preventing post-update misalignment. However, alignment is inherently context-dependent: a behavior that is aligned in one context may be inappropriate in another. For example, recommending that researchers retain their data for reproducibility is aligned, whereas recommending that a mobile app retain users' sensitive data may violate users' privacy. Starting from this observation, we identify a posttraining phenomenon where aligned training induces misaligned behavior in other contexts. We call this phenomenon context confusion. We demonstrate context confusion across three domains: (1) Gender Equality, (2) Privacy, and (3) Physical Safety. Unlike the broad misalignment seen in emergent misalignment, context confusion causes domain-specific misalignment that evades general alignment evaluations. Further, it is not effectively reduced by injecting general alignment training data, but can be substantially reduced by including targeted alignment data for the misaligned domain or providing in-context learning examples during inference. Lastly, we provide a mechanistic explanation of context confusion. We observe that queries from different domains can undergo similar representational shifts during the fine-tuning. Consequently, a query from a different domain may activate the same behavioral feature learned during fine-tuning, which causes the behavior to transfer to a context where it is misaligned. Based on our findings, we argue that it is difficult to predict the alignment state of a model after training by inspecting the training data alone, which highlights the importance of comprehensive post-training alignment evaluations.

cs.AI · cs.LG

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.79ACL Anthology · ACL 2026

Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness

Amin Banayeeanzade, Ala N. Tak University of Southern California, Fatemeh Bahrani University of Southern California, Anahita Bolourani University of California, Los Angeles, Leonardo Blas, Emilio Ferrara University of Southern California, Jonathan Gratch University of Southern California, Sai Praneeth Karimireddy University of Southern California

原文摘要

The ability to control LLMs’ emulated emotional states and personality traits is an essential step in enabling rich, human-centered interactions in socially interactive settings. We introduce PsySET, a Psychologically-informed benchmark to evaluate LLM Steering Effectiveness and Trustworthiness across the emotion and personality domains. Our study spans four models from different LLM families paired with various steering strategies, including prompting, fine-tuning, and representation engineering. Our results indicate that prompting is consistently effective but limited in intensity control, whereas vector injections achieve finer controllability while slightly reducing output quality. Moreover, we explore the trustworthiness of steered LLMs by assessing safety, truthfulness, fairness, and ethics, highlighting potential side effects and behavioral shifts. Notably, we observe idiosyncratic effects; for instance, even a positive emotion like joy can degrade robustness to adversarial factuality, lower privacy awareness, and increase preferential bias. Meanwhile, anger predictably elevates toxicity yet strengthens leakage resistance. Our framework establishes the first holistic evaluation of emotion and personality steering, offering insights into its interpretability and reliability for socially interactive applications.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表