English
Related papers

Related papers: Refusal Before Decoding: Detecting and Exploiting …

200 papers

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

This paper considers learning robot locomotion and manipulation tasks from expert demonstrations. Generative adversarial imitation learning (GAIL) trains a discriminator that distinguishes expert from agent transitions, and in turn use a…

Machine Learning · Computer Science 2022-06-24 Tianyu Wang , Nikhil Karnwal , Nikolay Atanasov

Pre-trained models have achieved remarkable success in natural language processing (NLP). However, existing pre-training methods underutilize the benefits of language understanding for generation. Inspired by the idea of Generative…

Computation and Language · Computer Science 2023-05-10 Jian Yang , Shuming Ma , Li Dong , Shaohan Huang , Haoyang Huang , Yuwei Yin , Dongdong Zhang , Liqun Yang , Furu Wei , Zhoujun Li

Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks by leveraging pre-trained (i.e., parametric) and external (i.e., contextual) knowledge. While substantial efforts have been made to enhance the…

Computation and Language · Computer Science 2025-05-19 Hyuhng Joon Kim , Youna Kim , Sang-goo Lee , Taeuk Kim

Safety alignment is crucial for large language models (LLMs) to resist malicious instructions but often results in over-refusals, where benign prompts are unnecessarily rejected, impairing user experience and model utility. We introduce…

Machine Learning · Computer Science 2025-07-08 Mahavir Dabas , Si Chen , Charles Fleming , Ming Jin , Ruoxi Jia

Learning latent representations has aided operational decision-making in several disciplines. Its advantages include uncovering hidden interactions in data and automating procedures which were performed manually in the past. Representation…

Machine Learning · Computer Science 2022-05-19 Christos Pylianidis , Ioannis N. Athanasiadis

Deep Reinforcement Learning (DRL) enables robots to learn complex behaviors through interaction with the environment. However, due to the unrestricted nature of the learning algorithms, the resulting solutions are often brittle and appear…

Robotics · Computer Science 2025-03-04 Oliver Hausdörfer , Alexander von Rohr , Éric Lefort , Angela Schoellig

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

Computation and Language · Computer Science 2025-10-01 Yuyou Zhang , Miao Li , William Han , Yihang Yao , Zhepeng Cen , Ding Zhao

Large Language Models (LLMs) are widely used across sectors, yet their alignment with International Humanitarian Law (IHL) is not well understood. This study evaluates eight leading LLMs on their ability to refuse prompts that explicitly…

Computers and Society · Computer Science 2025-06-10 John Mavi , Diana Teodora Găitan , Sergio Coronado

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Computation and Language · Computer Science 2025-10-13 John Hawkins , Aditya Pramar , Rodney Beard , Rohitash Chandra

AI-assisted code review is widely used to detect vulnerabilities before production release. Prior work shows that adversarial prompt manipulation can degrade large language model (LLM) performance in code generation. We test whether similar…

Cryptography and Security · Computer Science 2026-02-20 Scott Thornton

Neural network pretraining is gaining attention due to its outstanding performance in natural language processing applications. However, pretraining usually leverages predefined task sequences to learn general linguistic clues. The lack of…

Computation and Language · Computer Science 2021-06-08 Hongyin Luo , Shuyan Dong , Yung-Sung Chuang , Shang-Wen Li

Although achieving promising performance, recent analyses show that current generative large language models (LLMs) may still capture dataset biases and utilize them for generation, leading to poor generalizability and harmfulness of LLMs.…

Computation and Language · Computer Science 2024-09-02 Li Du , Zhouhao Sun , Xiao Ding , Yixuan Ma , Yang Zhao , Kaitao Qiu , Ting Liu , Bing Qin

Finetuning open-weight Large Language Models (LLMs) is standard practice for achieving task-specific performance improvements. Until now, finetuning has been regarded as a controlled and secure process in which training on benign datasets…

Machine Learning · Computer Science 2025-10-10 Thibaud Gloaguen , Mark Vero , Robin Staab , Martin Vechev

Data contamination poses a significant challenge to reliable LLM evaluation, where models may achieve high performance by memorizing training data rather than demonstrating genuine reasoning capabilities. We introduce RADAR (Recall vs.…

Artificial Intelligence · Computer Science 2025-10-13 Ashish Kattamuri , Harshwardhan Fartale , Arpita Vats , Rahul Raja , Ishita Prasad

Unified multimodal models can encode visual understanding and image generation within a shared backbone, yet understanding does not automatically translate into control: models may infer objects, relations, or knowledge cues but fail to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Fuxiang Zhai , Sixiang Chen , Yingjin Li , Shuaibo Li , Jianyu Lai , Tengjun Huang , Lei Zhu

Agentic language models compose multi step reasoning chains, yet intermediate steps can be corrupted by inconsistent context, retrieval errors, or adversarial inputs, which makes post hoc evaluation too late because errors propagate before…

Machine Learning · Computer Science 2025-11-11 Valentin Noël

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…

Computation and Language · Computer Science 2025-06-19 Xinyi Zeng , Yuying Shang , Jiawei Chen , Jingyuan Zhang , Yu Tian

Large Language Models' safety-aligned behaviors, such as refusing harmful queries, can be represented by linear directions in activation space. Previous research modeled safety behavior with a single direction, limiting mechanistic…

Computation and Language · Computer Science 2025-05-28 Wenbo Pan , Zhichao Liu , Qiguang Chen , Xiangyang Zhou , Haining Yu , Xiaohua Jia

Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the overrefusal problem…

Artificial Intelligence · Computer Science 2026-03-13 Zhiyu Xue , Zimo Qi , Guangliang Liu , Bocheng Chen , Ramtin Pedarsani
‹ Prev 1 4 5 6 7 8 10 Next ›