English
Related papers

Related papers: Thinking Wrong in Silence: Backdoor Attacks on Con…

200 papers

Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to…

Cryptography and Security · Computer Science 2026-01-29 Harsh Chaudhari , Ethan Rathbun , Hanna Foerster , Jamie Hayes , Matthew Jagielski , Milad Nasr , Ilia Shumailov , Alina Oprea

Many reasoning techniques for large multimodal models adapt language model approaches, such as Chain-of-Thought (CoT) prompting, which express reasoning as word sequences. While effective for text, these methods are suboptimal for…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Tan-Hanh Pham , Chris Ngo

Modern reasoning language models generate dense, sequential chain-of-thought traces implicitly assuming that every token contributes and that steps must be consumed in order. We challenge both assumptions through a systematic intervention…

Computation and Language · Computer Science 2026-05-11 Yi-Chang Chen , Feng-Ting Liao , Da-shan Shiu , Hung-yi Lee

Recent advances in large text-conditional diffusion models have revolutionized image generation by enabling users to create realistic, high-quality images from textual prompts, significantly enhancing artistic creation and visual…

Machine Learning · Computer Science 2025-07-08 Ali Naseh , Jaechul Roh , Eugene Bagdasarian , Amir Houmansadr

Large reasoning models (LRMs) generate extended solutions, yet it remains unclear whether these traces reflect substantive internal computation or merely verbosity and overthinking. Although recent hidden-state analyses suggest that…

Computation and Language · Computer Science 2026-05-05 Kotaro Furuya , Takahito Tanimura

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…

Artificial Intelligence · Computer Science 2026-05-29 Siddharth Sai , Xiaofei Wen , Muhao Chen

Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts with triggers that…

Computation and Language · Computer Science 2023-12-27 Xuan Sheng , Zhicheng Li , Zhaoyang Han , Xiangmao Chang , Piji Li

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…

Computation and Language · Computer Science 2022-11-23 Xuan Sheng , Zhaoyang Han , Piji Li , Xiangmao Chang

Chain-of-thought (CoT) reasoning has become a central mechanism for eliciting multi-step reasoning in Large Language Models (LLMs). Yet recent evidence presents a tension: hidden states appear to already encode future reasoning before CoT…

Machine Learning · Computer Science 2026-05-29 Liyan Xu , Mo Yu , Fandong Meng , Jie Zhou

Chain-of-thought and more broadly test-time compute are known to augment the expressive capabilities of language models and have led to major innovations in reasoning. Motivated by this success, this paper explores latent chain-of-thought…

Machine Learning · Computer Science 2026-05-20 Carson Dudley , Samet Oymak

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…

Cryptography and Security · Computer Science 2025-09-29 Xiyu Zeng , Siyuan Liang , Liming Lu , Haotian Zhu , Enguang Liu , Jisheng Dang , Yongbin Zhou , Shuchao Pang

Despite the strong performance of large language models (LLMs) across diverse tasks, their susceptibility to adversarial attacks and unsafe content generation remains a significant obstacle to deployment, particularly in high-stakes…

Machine Learning · Computer Science 2026-05-25 Thanh Q. Tran , Arun Verma , Kiwan Wong , Bryan Kian Hsiang Low , Daniela Rus , Wei Xiao

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

Cryptography and Security · Computer Science 2022-05-31 Sangeet Sagar , Abhinav Bhatt , Abhijith Srinivas Bidaralli

Reasoning-capable large language models solve hard problems by emitting long chains of thought, paying heavily in latency, GPU time, and energy. Casual inspection of their traces reveals extensive reformulation, verification, and circular…

Artificial Intelligence · Computer Science 2026-05-26 Zhiyuan Zhai , Xinkai You , Wenjing Yan , Xin Wang

Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: performance often peaks at a certain iteration depth and then collapses with further recurrence.…

Machine Learning · Computer Science 2026-05-27 Xiao-Wen Yang , Ziyu Han , Xi-Hua Zhang , Wen-Da Wei , Jie-Jing Shao , Lan-Zhe Guo , Yu-Feng Li

The internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute. However, existing activation steering methods rely on static control vectors that fail to adapt…

Machine Learning · Computer Science 2026-02-06 Zhenning Shi , Yijia Zhu , Junhan Shi , Xun Zhang , Lei Wang , Congcong Miao

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose…

Computation and Language · Computer Science 2026-05-14 Liang Lin , Miao Yu , Moayad Aloqaily , Zhenhong Zhou , Kun Wang , Linsey Pang , Prakhar Mehrotra , Qingsong Wen

The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…

Cryptography and Security · Computer Science 2023-10-19 Ganghua Wang , Xun Xian , Jayanth Srinivasa , Ashish Kundu , Xuan Bi , Mingyi Hong , Jie Ding

Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step…

Computation and Language · Computer Science 2026-03-09 Yunlong Chu , Minglai Shao , Yuhang Liu , Bing Hao , Yumeng Lin , Jialu Wang , Ruijie Wang

Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and leaving potential reasoning capacity untapped. The State Stream Transformer (SST) V2 enables…

Machine Learning · Computer Science 2026-05-04 Thea Aviss
‹ Prev 1 3 4 5 6 7 10 Next ›