English
Related papers

Related papers: GRP-Obliteration: Unaligning LLMs With a Single Un…

200 papers

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Computation and Language · Computer Science 2026-02-25 Xing Li , Hui-Ling Zhen , Lihao Yin , Xianzhi Yu , Zhenhua Dong , Mingxuan Yuan

The promising zero-shot generalization of vision-language models such as CLIP has led to their adoption using prompt learning for numerous downstream tasks. Previous works have shown test-time prompt tuning using entropy minimization to…

Computer Vision and Pattern Recognition · Computer Science 2024-01-12 Jameel Hassan , Hanan Gani , Noor Hussein , Muhammad Uzair Khattak , Muzammal Naseer , Fahad Shahbaz Khan , Salman Khan

Test-time prompt tuning for vision-language models has demonstrated impressive generalization capabilities under zero-shot settings. However, tuning the learnable prompts solely based on unlabeled test data may induce prompt optimization…

Machine Learning · Computer Science 2025-11-18 Fei Song , Yi Li , Rui Wang , Jiahuan Zhou , Changwen Zheng , Jiangmeng Li

Vision-language models (VLMs), such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstream tasks. However, due to their inherent vulnerability and…

Machine Learning · Computer Science 2025-08-28 Lijun Sheng , Jian Liang , Zilei Wang , Ran He

Reasoning language models can solve increasingly complex tasks, but struggle to produce the calibrated confidence estimates necessary for reliable deployment. Existing calibration methods usually depend on labels or repeated sampling at…

Machine Learning · Computer Science 2026-04-22 Thomas Zollo , Jimmy Wang , Richard Zemel

One of the most impressive results of recent NLP history is the ability of pre-trained language models to solve new tasks in a zero-shot setting. To achieve this, NLP tasks are framed as natural language prompts, generating a response…

Computation and Language · Computer Science 2022-12-29 Chunting Zhou , Junxian He , Xuezhe Ma , Taylor Berg-Kirkpatrick , Graham Neubig

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

Cryptography and Security · Computer Science 2026-01-28 Yangyang Guo , Ziwei Xu , Si Liu , Zhiming Zheng , Mohan Kankanhalli

In recent years, prompt tuning has proven effective in adapting pre-trained vision-language models to downstream tasks. These methods aim to adapt the pre-trained models by introducing learnable prompts while keeping pre-trained weights…

Computer Vision and Pattern Recognition · Computer Science 2023-11-13 Dongjun Lee , Seokwon Song , Jihee Suh , Joonmyung Choi , Sanghyeok Lee , Hyunwoo J. Kim

How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for a wide range of NLP tasks. However, existing approaches…

Computation and Language · Computer Science 2023-05-29 Xuandong Zhao , Siqi Ouyang , Zhiguo Yu , Ming Wu , Lei Li

Large language models (LLMs) have become increasingly capable of following instructions and complex reasoning, making prompting a flexible interface for adapting models without parameter updates. Yet prompt design remains labor-intensive…

Computation and Language · Computer Science 2026-05-22 Farima Fatahi Bayat , Moin Aminnaseri , Pouya Pezeshkpour , Estevam Hruschka

We present SelfPrompt, a novel prompt-tuning approach for vision-language models (VLMs) in a semi-supervised learning setup. Existing methods for tuning VLMs in semi-supervised setups struggle with the negative impact of the miscalibrated…

Computer Vision and Pattern Recognition · Computer Science 2025-01-30 Shuvendu Roy , Ali Etemad

Large language models used for clinical abstraction are sensitive to prompt wording, yet most work treats prompts as fixed and studies uncertainty in isolation. We argue these should be treated jointly. Across two clinical tasks (MedAlign…

Computation and Language · Computer Science 2026-02-02 Arinbjörn Kolbeinsson , Daniel Timbie , Sajjan Narsinghani , Sanjay Hariharan

Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…

Machine Learning · Computer Science 2025-02-28 Xiyue Peng , Hengquan Guo , Jiawei Zhang , Dongqing Zou , Ziyu Shao , Honghao Wei , Xin Liu

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

Computation and Language · Computer Science 2026-03-23 Zafir Shamsi , Nikhil Chekuru , Zachary Guzman , Shivank Garg

Single-prompt first-token probabilities from zero-shot vision-language model (VLM) safety classifiers are treated as decision scores, but we show they are unreliable under semantically equivalent prompt reformulation: even when the binary…

Computation and Language · Computer Science 2026-05-04 Charles Weng , Dingwen Li , Alexander Martin

What kinds of instructional prompts are easier to follow for Language Models (LMs)? We study this question by conducting extensive empirical analysis that shed light on important features of successful instructional prompts. Specifically,…

Computation and Language · Computer Science 2022-03-17 Swaroop Mishra , Daniel Khashabi , Chitta Baral , Yejin Choi , Hannaneh Hajishirzi

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…

Machine Learning · Computer Science 2025-09-29 Sathwik Karnik , Somil Bansal

Test-time prompt tuning (TPT) has emerged as a promising technique for enhancing the adaptability of vision-language models by optimizing textual prompts using unlabeled test data. However, prior studies have observed that TPT often…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Hyeonseo Jang , Jaebyeong Jeon , Joong-Won Hwang , Kibok Lee

Assessing risk of bias (RoB) in randomized controlled trials is essential for trustworthy evidence synthesis, but the process is resource-intensive and prone to variability across reviewers. Large language models (LLMs) offer a route to…

Artificial Intelligence · Computer Science 2025-12-02 Lingbo Li , Anuradha Mathrani , Teo Susnjak

As large language models (LLMs) are increasingly integrated into numerous applications across various domains, LLMs' safety becomes a critical concern for both application developers and intended users. Currently, great efforts have been…

Cryptography and Security · Computer Science 2025-09-30 Haoran Li , Yulin Chen , Jingru Zeng , Hao Peng , Huihao Jing , Wenbin Hu , Xi Yang , Ziqian Zeng , Sirui Han , Yangqiu Song