English
Related papers

Related papers: Guardrails in Logit Space: Safety Token Regulariza…

200 papers

Aligned LLMs are secure, capable of recognizing and refusing to answer malicious questions. However, the role of internal parameters in maintaining such security is not well understood yet, further these models can be vulnerable to security…

Cryptography and Security · Computer Science 2025-04-08 Shen Li , Liuyi Yao , Lan Zhang , Yaliang Li

Aligning large language models (LLMs) with human values is crucial for safe deployment. Inference-time techniques offer granular control over generation; however, they rely on model uncertainty, meaning an internal estimate of how likely…

Computation and Language · Computer Science 2026-03-04 Mohammad Atif Quamar , Mohammad Areeb , Mikhail Kuznetsov , Muslum Ozgur Ozmen , Z. Berkay Celik

Reinforcement learning (RL) has become a cornerstone for enhancing the reasoning capabilities of large language models (LLMs), with recent innovations such as Group Relative Policy Optimization (GRPO) demonstrating exceptional…

Computation and Language · Computer Science 2025-05-20 Zhihe Yang , Xufang Luo , Zilong Wang , Dongqi Han , Zhiyuan He , Dongsheng Li , Yunjian Xu

Large Language Models (LLMs) are increasingly being integrated into services such as ChatGPT to provide responses to user queries. To mitigate potential harm and prevent misuse, there have been concerted efforts to align the LLMs with human…

Cryptography and Security · Computer Science 2024-12-30 Xiaomeng Hu , Pin-Yu Chen , Tsung-Yi Ho

This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing. We utilized a logit lens technique to analyze the model's token predictions derived from intermediate…

Computation and Language · Computer Science 2025-06-10 Jaturong Kongmanee

LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore…

Computation and Language · Computer Science 2024-10-01 Sachin Kumar

As large language models (LLMs) are increasingly fine-tuned for hardware tasks like RTL code generation, the scarcity of high-quality datasets often leads to the use of rapidly assembled or generated training data. These datasets frequently…

Cryptography and Security · Computer Science 2026-05-01 Mahshid Rezakhani , Nowfel Mashnoor , Kimia Azar , Hadi Kamali

Speculative decoding accelerates inference in large language models (LLMs) by generating multiple draft tokens simultaneously. However, existing methods often struggle with token misalignment between the training and decoding phases,…

Computation and Language · Computer Science 2025-10-21 Shijing Hu , Jingyang Li , Xingyu Xie , Zhihui Lu , Kim-Chuan Toh , Pan Zhou

Recent work has shown that fine-tuning large language models (LLMs) on code with security vulnerabilities can result in misaligned and unsafe behaviors across broad domains. These results prompted concerns about the emergence of harmful…

Machine Learning · Computer Science 2025-07-08 Jeremiah Giordani

Training large language models (LLMs) from scratch can yield models with unique functionalities and strengths, but it is costly and often leads to redundant capabilities. A more cost-effective alternative is to fuse existing pre-trained…

Computation and Language · Computer Science 2025-09-23 Runjia Zeng , James Chenhao Liang , Cheng Han , Zhiwen Cao , Jiahao Liu , Xiaojun Quan , Yingjie Victor Chen , Lifu Huang , Tong Geng , Qifan Wang , Dongfang Liu

Large language models (LLMs) have shown great potential as general-purpose AI assistants across various domains. To fully leverage this potential in specific applications, many companies provide fine-tuning API services, enabling users to…

Machine Learning · Computer Science 2025-05-20 Ning Lu , Shengcai Liu , Jiahao Wu , Weiyu Chen , Zhirui Zhang , Yew-Soon Ong , Qi Wang , Ke Tang

Vision-language-action (VLA) models can learn to perform diverse manipulation skills "out of the box," but achieving the precision and speed that real-world tasks demand requires further fine-tuning -- for example, via reinforcement…

Machine Learning · Computer Science 2026-05-04 Charles Xu , Jost Tobias Springenberg , Michael Equi , Ali Amin , Adnan Esmail , Sergey Levine , Liyiming Ke

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Computation and Language · Computer Science 2026-02-26 Mengxuan Hu , Vivek V. Datla , Anoop Kumar , Zihan Guan , Sheng Li , Alfy Samuel , Daben Liu

Scientific software relies on high-precision computation, yet finite floating-point representations can introduce precision errors that propagate in safety-critical domains. Despite the growing use of large language models (LLMs) in…

Software Engineering · Computer Science 2026-04-10 Tien Nguyen , Kirshanthan Sundararajah , Muhammad Ali Gulzar

Fine-tuning aligned language models on benign tasks unpredictably degrades safety guardrails, even when training data contains no harmful content and developers have no adversarial intent. We show that the prevailing explanation, that…

The widespread adoption of large language models (LLMs) has increased concerns about their robustness. Vulnerabilities in perturbations of tokenisation of the input indicate that models trained with a deterministic canonical tokenisation…

Computation and Language · Computer Science 2026-04-20 Sophie Steger , Rui Li , Sofiane Ennadir , Anya Sims , Arno Solin , Franz Pernkopf , Martin Trapp

Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful content generation, LLMs are often still vulnerable to…

Machine Learning · Computer Science 2025-01-29 Ryo Hase , Md Rafi Ur Rashid , Ashley Lewis , Jing Liu , Toshiaki Koike-Akino , Kieran Parsons , Ye Wang

Fine-tuning large language models (LLMs) on telecom datasets is a common practice to adapt general-purpose models to the telecom domain. However, little attention has been paid to how this process may compromise model safety. Recent…

Computers and Society · Computer Science 2026-02-09 Aladin Djuhera , Swanand Ravindra Kadhe , Farhan Ahmed , Syed Zawad , Fernando Koch , Walid Saad , Holger Boche

Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EMA): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target…

Machine Learning · Computer Science 2026-03-06 David Kaczér , Magnus Jørgenvåg , Clemens Vetter , Esha Afzal , Robin Haselhorst , Lucie Flek , Florian Mai

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Computation and Language · Computer Science 2025-10-31 Xuandong Zhao , Will Cai , Tianneng Shi , David Huang , Licong Lin , Song Mei , Dawn Song
‹ Prev 1 8 9 10 Next ›