English
Related papers

Related papers: Controllable Reasoning Models Are Private Thinkers

200 papers

We study privacy leakage in the reasoning traces of large reasoning models used as personal agents. Unlike final outputs, reasoning traces are often assumed to be internal and safe. We challenge this assumption by showing that reasoning…

Computation and Language · Computer Science 2025-10-02 Tommaso Green , Martin Gubri , Haritz Puerto , Sangdoo Yun , Seong Joon Oh

The ability of large language models (LLMs) to follow user instructions is central to their reliability, safety, and usefulness. While prior studies assess instruction adherence in the model's main responses, we argue that it is also…

Machine Learning · Computer Science 2025-10-20 Yongchan Kwon , Shang Zhu , Federico Bianchi , Kaitlyn Zhou , James Zou

As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…

Machine Learning · Computer Science 2025-08-28 Dylan Sam , Alexander Robey , Andy Zou , Matt Fredrikson , J. Zico Kolter

AI-powered planning tools show promise in supporting programming learners by enabling early, formative feedback on their thinking processes prior to coding. To date, however, most AI-supported planning tools rely on students'…

Human-Computer Interaction · Computer Science 2026-02-04 Yoshee Jain , Heejin Do , Zihan Wu , April Yi Wang

Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated that strong performance of language models comes along with…

Cryptography and Security · Computer Science 2021-02-24 Huseyin A. Inan , Osman Ramadan , Lukas Wutschitz , Daniel Jones , Victor Rühle , James Withers , Robert Sim

Instruction-following is essential for aligning large language models (LLMs) with user intent. While recent reasoning-oriented models exhibit impressive performance on complex mathematical problems, their ability to adhere to natural…

Computation and Language · Computer Science 2025-05-27 Tingchen Fu , Jiawei Gu , Yafu Li , Xiaoye Qu , Yu Cheng

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…

Machine Learning · Computer Science 2023-05-31 Stephan Rabanser , Anvith Thudi , Abhradeep Thakurta , Krishnamurthy Dvijotham , Nicolas Papernot

Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved. Recent work suggests…

Computation and Language · Computer Science 2026-03-12 Prince Kumar , Rudra Murthy , Riyaz Bhat , Danish Contractor

Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…

Human-Computer Interaction · Computer Science 2025-10-07 Zhiping Zhang , Bingcan Guo , Tianshi Li

Large reasoning models (LRMs) have recently demonstrated impressive capabilities in complex reasoning tasks by leveraging increased test-time computation and exhibiting behaviors reminiscent of human-like self-reflection. While LRMs show a…

Computation and Language · Computer Science 2025-10-21 Qingcheng Zeng , Weihao Xuan , Leyang Cui , Rob Voigt

Many current Internet services rely on inferences from models trained on user data. Commonly, both the training and inference tasks are carried out using cloud resources fed by personal data collected at scale from users. Holding and using…

Machine Learning · Computer Science 2018-04-04 Sandra Servia-Rodriguez , Liang Wang , Jianxin R. Zhao , Richard Mortier , Hamed Haddadi

Machine learning models leak information about their training data every time they reveal a prediction. This is problematic when the training data needs to remain private. Private prediction methods limit how much information about the…

Machine Learning · Computer Science 2020-07-13 Laurens van der Maaten , Awni Hannun

Reasoning models excel in complex problem solving but exhibit a concerning trade off between reasoning capabilities and instruction following abilities. Existing approaches for improving instruction following rely on stronger external…

Artificial Intelligence · Computer Science 2025-08-05 Qingyu Ren , Qianyu He , Bowei Zhang , Jie Zeng , Jiaqing Liang , Yanghua Xiao , Weikang Zhou , Zeye Sun , Fei Yu

Large Reasoning Models (LRMs) improve performance, reliability, and interpretability by generating explicit chain-of-thought (CoT) reasoning, but this transparency introduces a serious privacy risk: intermediate reasoning often leaks…

Artificial Intelligence · Computer Science 2026-01-09 Arghyadeep Das , Sai Sreenivas Chintha , Rishiraj Girmal , Kinjal Pandey , Sharvi Endait

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…

Computation and Language · Computer Science 2022-12-20 Joel Jang , Dongkeun Yoon , Sohee Yang , Sungmin Cha , Moontae Lee , Lajanugen Logeswaran , Minjoon Seo

As programmers write code, they often edit and retry multiple times, creating rich "interaction traces" that reveal how they approach coding tasks and provide clues about their level of skill development. For novice programmers in…

Machine Learning · Computer Science 2026-04-16 Alexis Ross , Megha Srivastava , Jeremiah Blanchard , Jacob Andreas

Can we trust the reasoning traces that large reasoning models (LRMs) produce? We investigate whether these traces faithfully reflect what drives model outputs, and whether models will honestly report their influence. We introduce Thought…

Artificial Intelligence · Computer Science 2026-03-24 Yijie Hao , Lingjie Chen , Ali Emami , Joyce Ho

We present the surprising finding that a language model's reasoning capabilities can be improved by training on synthetic datasets of chain-of-thought (CoT) traces from more capable models, even when all of those traces lead to an incorrect…

Artificial Intelligence · Computer Science 2026-01-26 Abhranil Chandra , Ayush Agrawal , Arian Hosseini , Sebastian Fischmeister , Rishabh Agarwal , Navin Goyal , Aaron Courville

AI systems that output their reasoning in natural language offer an opportunity for safety -- we can \emph{monitor} their chain of thought (CoT) for undesirable reasoning, such as the pursuit of harmful objectives. However, the extent to…

Artificial Intelligence · Computer Science 2025-12-10 Matt MacDermott , Qiyao Wei , Rada Djoneva , Francis Rhys Ward

Language model-based instruction-following systems have lately shown increasing performance on many benchmark tasks, demonstrating the capability of adapting to a broad variety of instructions. However, such systems are often not designed…

Computation and Language · Computer Science 2024-03-20 Rahul Nadkarni , Yizhong Wang , Noah A. Smith
‹ Prev 1 2 3 10 Next ›