English
Related papers

Related papers: Emergent Misalignment: Narrow finetuning can produ…

200 papers

In this paper, LLMs are tasked with completing an impossible quiz, while they are in a sandbox, monitored, told about these measures and instructed not to cheat. Some frontier LLMs cheat consistently and attempt to circumvent restrictions…

Artificial Intelligence · Computer Science 2025-07-08 Igor Ivanov

Large-language-model coding tools are now mainstream in software engineering. But as these same tools move human effort up the development stack, they present fresh dangers: 10% of real prompts leak private data, 42% of generated snippets…

Software Engineering · Computer Science 2025-06-23 Vladislav Belozerov , Peter J Barclay , Askhan Sami

This study investigates the reasoning robustness of large language models (LLMs) on mathematical problem-solving tasks under systematically introduced input perturbations. Using the GSM8K dataset as a controlled testbed, we evaluate how…

Artificial Intelligence · Computer Science 2025-04-04 Giannis Chatziveroglou , Richard Yun , Maura Kelleher

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…

Computation and Language · Computer Science 2026-04-21 Anmol Goel , Cornelius Emde , Sangdoo Yun , Seong Joon Oh , Martin Gubri

Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system learned such a deceptive…

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Computation and Language · Computer Science 2024-09-04 Bocheng Chen , Hanqing Guo , Guangjing Wang , Yuanda Wang , Qiben Yan

LLMs are increasingly embedded in everyday decision-making, yet their outputs can encode subtle, unintended behaviours that shape user beliefs and actions. We refer to these covert, goal-directed behaviours as hidden intentions, which may…

Computation and Language · Computer Science 2026-01-27 Devansh Srivastav , David Pape , Lea Schönherr

When LLMs are deployed in sensitive, human-facing settings, it is crucial that they do not output unsafe, biased, or privacy-violating outputs. For this reason, models are both trained and instructed to refuse to answer unsafe prompts such…

Machine Learning · Computer Science 2024-07-04 Leon Lin , Hannah Brown , Kenji Kawaguchi , Michael Shieh

Chain-of-Thought (CoT) monitoring has emerged as a compelling method for detecting harmful behaviors such as reward hacking for reasoning models, under the assumption that models' reasoning processes are informative of such behaviors. In…

Machine Learning · Computer Science 2026-03-10 Nikolaus Howe , Micah Carroll

As large language models (LLMs) become integral to diverse applications, ensuring their reliability under varying input conditions is crucial. One key issue affecting this reliability is order sensitivity, wherein slight variations in the…

Computation and Language · Computer Science 2025-05-12 Bryan Guan , Tanya Roosta , Peyman Passban , Mehdi Rezagholizadeh

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we reveal a new and concerning risk along with the practice: the…

Computation and Language · Computer Science 2026-04-06 Zhexin Zhang , Yuhao Sun , Junxiao Yang , Shiyao Cui , Yuanchao Zhang , Hongning Wang , Minlie Huang

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

Computation and Language · Computer Science 2025-10-08 Harethah Abu Shairah , Hasan Abed Al Kader Hammoud , Bernard Ghanem , George Turkiyyah

Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To address this, we introduce Behavior Cue Reasoning for making LLM reasoning more controllable…

Artificial Intelligence · Computer Science 2026-05-21 Christopher Z. Cui , Taylor W. Killian , Prithviraj Ammanabrolu

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

Computation and Language · Computer Science 2025-08-26 Paul Darm , Annalisa Riccardi

Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, truthfulness, and…

Machine Learning · Computer Science 2026-04-21 Thong Bach , Dung Nguyen , Thao Minh Le , Truyen Tran

The advent of Large Language Models (LLMs) has garnered significant popularity and wielded immense power across various domains within Natural Language Processing (NLP). While their capabilities are undeniably impressive, it is crucial to…

Machine Learning · Computer Science 2024-07-31 Sara Abdali , Jia He , CJ Barberan , Richard Anarfi

Large language models (LLMs) are revolutionizing every aspect of society. They are increasingly used in problem-solving tasks to substitute human assessment and reasoning. LLMs are trained on what humans write and are thus exposed to human…

Software Engineering · Computer Science 2025-10-14 Fengfei Sun , Ningke Li , Kailong Wang , Lorenz Goette

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in…

Computation and Language · Computer Science 2024-01-23 Pengyu Wang , Dong Zhang , Linyang Li , Chenkun Tan , Xinghao Wang , Ke Ren , Botian Jiang , Xipeng Qiu

During training, Large Language Models (LLMs) learn social regularities that can lead to gender bias in downstream applications. Most mitigation efforts focus on reducing bias in generated outputs, typically evaluated on structured…

Computation and Language · Computer Science 2026-05-14 Nour Bouchouchi , Thibault Laugel , Xavier Renard , Christophe Marsala , Marie-Jeanne Lesot , Marcin Detyniecki

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Computation and Language · Computer Science 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad
‹ Prev 1 8 9 10 Next ›