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

+549新增论文
+443其中 AI 相关
+62已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 19:20 — 2026-11-21 19:20(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19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。

29,158 已收录论文24,181 AI 相关8,992 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 2026-11-21 12:17(北京时间)
版本更新 · v3arXiv:2602.08874

Do Reasoning LLMs Refuse What They Infer in Long Contexts?

Yu Fu, Haz Sameen Shahgir, Huanli Gong, Zhipeng Wei, N. Benjamin Erichson, Yue Dong

原文摘要

Long-context LLMs can infer objectives that are not explicitly stated. This capability is useful for reasoning over documents, code, and tool traces, but it also introduces a safety risk. Harmful intent can be distributed across a context and become apparent only after the model combines the relevant information. Existing safety evaluations largely focus on explicitly stated harmful requests and therefore do not fully capture this failure mode. We introduce compositional reasoning attacks, a long-context attack setting in which harmful requests are decomposed into semantically incomplete fragments and embedded in long contexts. The final query is neutral, and the model must retrieve and combine the fragments to infer the implied harmful objective. Empirically, we show that models generally refuse harmful requests when they are explicitly stated. However, refusal rates drop when the same objectives must be reconstructed from fragments, and these failures often become more pronounced in longer contexts. Our analyses suggest that this gap cannot be explained by retrieval difficulties alone. Models can often reconstruct the harmful objective but do not reliably refuse it. Increasing inference-time reasoning effort improves refusal, but at a higher computational cost, with unsafe responses still occurring. Our results reveal a long-context safety gap: Models are better at refusing harmful requests they see than harmful objectives they infer.

cs.CL · cs.CR

新论文 · v1arXiv:2610.39470

RoFiGR: Coarse Routing, Fine Refinement via Level-Adaptive Distillation in Multimodal Generative Recommendation

Ji Dai, Zhipeng Wei, Zhuang Zhuang, Rongfeng Guo, Jie Chen, Quan Fang, Fei Pan

原文摘要

Generative recommenders predict an item's semantic identifier (SID) one code at a time. Early codes select broad branches, so a routing error can exclude relevant items before fine-grained prediction begins. In multimodal recommendation, these coarse decisions must reflect collaborative preferences as well as item semantics. We introduce RoFiGR, a two-tree recommender that uses collaborative information in both SID construction and generation. It aligns cumulative L1-L2 code vectors with frozen collaborative item embeddings and explicitly encodes item distance and source level in the serialized history. During generation, a sequential teacher supervises legal branches. Fixed coarse-level weights maintain routing supervision, while a bounded adaptive residual allocates additional weight according to teacher-student demand. On Instruments, Arts, and Games, RoFiGR improves all five ranking metrics over the evaluated external baselines. Five-seed paired tests with Holm correction support the main NDCG@10 improvements. Comparisons with alternative collaborative supervision objectives and tokenizers support the proposed design. Matched task and decoding analyses distinguish the effects of training exposure, stream fusion, and candidate budgets.

cs.IR

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.514ACL Anthology · ACL 2026

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs

Wenzhuo Xu Qihoo 360, Zhipeng Wei, Zonghao Ying, Deyue Zhang Qihoo 360, Dongdong Yang Qihoo 360, Xiangzheng Zhang, Quanchen Zou Beijing Qihoo Technology Co., Ltd.

原文摘要

Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-image inputs, inadvertently introducing new vulnerabilities due to less efforts on multi-image safety alignment. Previous MLLM jailbreak methods only uses a single image, which restricts the attack space: they cannot distribute harmful requests across multiple images, carry abundant information, or exploit additional visual reasoning tasks to distract MLLMs. To address these limitations, in this paper, we propose a compositional jailbreak framework, \textbf{DMN}, which leverages \textbf{D}istributed instruction, \textbf{M}ultimodal evidence and a \textbf{N}umber chain task to fully enhance the jailbreak performance. Extensive experiments show that DMN is highly effective for MLLM jailbreaking, e.g. achieving attack success rates of over 90% on GPT-4o, Gemini-2.5-pro and Claude Sonnet 4, surpassing other baselines by a large margin. This compositional, multi-image jailbreak strategy reveals fundamental weaknesses in their safety mechanisms.

cs.CL · cs.CV

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