English
Related papers

Related papers: Leaky Thoughts: Large Reasoning Models Are Not Pri…

200 papers

Recent advances in large reasoning models (LRMs) have enabled strong chain-of-thought (CoT) generation through test-time computation. While these multi-step reasoning capabilities represent a major milestone in language model performance,…

Artificial Intelligence · Computer Science 2025-10-14 Changsheng Wang , Chongyu Fan , Yihua Zhang , Jinghan Jia , Dennis Wei , Parikshit Ram , Nathalie Baracaldo , Sijia Liu

Recent work explores latent reasoning to improve reasoning efficiency by replacing explicit reasoning trajectories with continuous representations in a latent space, yet its effectiveness varies across settings. Analysis of model confidence…

Artificial Intelligence · Computer Science 2026-02-13 Xin Xu , Tong Yu , Xiang Chen , Haoliang Wang , Julian McAuley , Saayan Mitra

Micro-expressions have drawn increasing interest lately due to various potential applications. The task is, however, difficult as it incorporates many challenges from the fields of computer vision, machine learning and emotional sciences.…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Tuomas Varanka , Yante Li , Wei Peng , Guoying Zhao

Synthetic data inherits the differential privacy guarantees of the model used to generate it. Additionally, synthetic data may benefit from privacy amplification when the generative model is kept hidden. While empirical studies suggest this…

Machine Learning · Computer Science 2025-06-06 Clément Pierquin , Aurélien Bellet , Marc Tommasi , Matthieu Boussard

This paper presents a novel approach to evaluating the security of large language models (LLMs) against prompt leakage-the exposure of system-level prompts or proprietary configurations. We define prompt leakage as a critical threat to…

Cryptography and Security · Computer Science 2025-02-19 Tvrtko Sternak , Davor Runje , Dorian Granoša , Chi Wang

This paper introduces a new attack on recent messaging systems that protect communication metadata. The main observation is that if an adversary manages to compromise a user's friend, it can use this compromised friend to learn information…

Cryptography and Security · Computer Science 2018-10-25 Sebastian Angel , David Lazar , Ioanna Tzialla

Learning analytics researchers often analyze qualitative student data such as coded annotations or interview transcripts to understand learning processes. With the rise of generative AI, fully automated and human-AI workflows have emerged…

Computation and Language · Computer Science 2026-01-21 Elham Tajik , Conrad Borchers , Bahar Shahrokhian , Sebastian Simon , Ali Keramati , Sonika Pal , Sreecharan Sankaranarayanan

Reasoning Language Models (RLMs) have gained traction for their ability to perform complex, multi-step reasoning tasks through mechanisms such as Chain-of-Thought (CoT) prompting or fine-tuned reasoning traces. While these capabilities…

Computation and Language · Computer Science 2025-07-04 Riccardo Cantini , Nicola Gabriele , Alessio Orsino , Domenico Talia

Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicited via Chain-of-Thought (CoT) practices. However, whether fundamental reasoning…

Computation and Language · Computer Science 2026-05-28 Xingwei Tan , Marco Valentino , Mahmud Elahi Akhter , Yuxiang Zhou , Maria Liakata , Nikolaos Aletras

Chain-of-Thought (CoT) reasoning has significantly advanced state-of-the-art AI capabilities. However, recent studies have shown that CoT reasoning is not always faithful when models face an explicit bias in their prompts, i.e., the CoT can…

Artificial Intelligence · Computer Science 2025-06-18 Iván Arcuschin , Jett Janiak , Robert Krzyzanowski , Senthooran Rajamanoharan , Neel Nanda , Arthur Conmy

LLMs driven products were increasingly prevalent in our daily lives, With a natural language based interaction style, people may potentially leak their personal private information. Thus, privacy policy and user agreement played an…

Human-Computer Interaction · Computer Science 2024-06-27 Shuning Zhang , Haobin Xing , Xin Yi , Hewu Li

The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the training set can be reconstructed directly from model parameters.…

Machine Learning · Computer Science 2025-09-26 Yehonatan Refael , Guy Smorodinsky , Ofir Lindenbaum , Itay Safran

Reasoning models often exhibit overthinking, characterized by redundant reasoning steps. We identify \emph{internal bias} elicited by the input question as a key trigger of such behavior. Upon encountering a problem, the model immediately…

Artificial Intelligence · Computer Science 2026-03-03 Renfei Dang , Zhening Li , Shujian Huang , Jiajun Chen

The emergence of social and technological networks has enabled rapid sharing of data and information. This has resulted in significant privacy concerns where private information can be either leaked or inferred from public data. The problem…

Data Structures and Algorithms · Computer Science 2015-11-20 Fragkiskos Koufogiannis , George Pappas

Behavioral simulation and strategic problem solving are different tasks. Large language models are increasingly explored as agents in policy-facing institutional simulations, but stronger reasoning need not improve behavioral sampling. We…

Machine Learning · Computer Science 2026-05-07 Sandro Andric

Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning…

Computation and Language · Computer Science 2022-09-12 Jimit Majmudar , Christophe Dupuy , Charith Peris , Sami Smaili , Rahul Gupta , Richard Zemel

Large Language Models (LLMs) are extensively used today across various sectors, including academia, research, business, and finance, for tasks such as text generation, summarization, and translation. Despite their widespread adoption, these…

Computation and Language · Computer Science 2024-04-26 Yash Saxena , Sarthak Chopra , Arunendra Mani Tripathi

Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII), which can violate privacy regulations and compromise individual…

When pieces from an individual's personal information available online are connected over time and across multiple platforms, this more complete digital trace can give unintended insights into their life and opinions. In a data narrative…

Human-Computer Interaction · Computer Science 2022-04-06 Emma Nicol , Jo Briggs , Wendy Moncur , Amal Htait , Daniel Carey , Leif Azzopardi , Burkhard Schafer

SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sensitive information, fine-tune on proprietary recordings, or both. We identify and…

Computation and Language · Computer Science 2026-05-28 Maike Züfle , Jan Niehues
‹ Prev 1 8 9 10 Next ›