English
Related papers

Related papers: Fake Alignment: Are LLMs Really Aligned Well?

200 papers

Like a criminal under investigation, Large Language Models (LLMs) might pretend to be aligned while evaluated and misbehave when they have a good opportunity. Can current interpretability methods catch these 'alignment fakers?' To answer…

Computation and Language · Computer Science 2024-05-14 Joshua Clymer , Caden Juang , Severin Field

Fine-tuning Large Language Models (LLMs) on some task-specific datasets has been a primary use of LLMs. However, it has been empirically observed that this approach to enhancing capability inevitably compromises safety, a phenomenon also…

Machine Learning · Statistics 2025-03-28 Pin-Yu Chen , Han Shen , Payel Das , Tianyi Chen

Large Language Models (LLMs) have demonstrated potential in cybersecurity applications but have also caused lower confidence due to problems like hallucinations and a lack of truthfulness. Existing benchmarks provide general evaluations but…

Confidence calibration is essential for making large language models (LLMs) reliable, yet existing training-free methods have been primarily studied under single-answer question answering. In this paper, we show that these methods break…

Computation and Language · Computer Science 2026-02-10 Yuhan Wang , Shiyu Ni , Zhikai Ding , Zihang Zhan , Yuanzi Li , Keping Bi

Large Language Models (LLMs) exhibit remarkable fluency and competence across various natural language tasks. However, recent research has highlighted their sensitivity to variations in input prompts. To deploy LLMs in a safe and reliable…

Computation and Language · Computer Science 2025-04-30 Harsh Raj , Vipul Gupta , Domenic Rosati , Subhabrata Majumdar

As large language models attract increasing attention and find widespread application, concurrent challenges of reliability also arise at the same time. Confidence calibration, an effective analysis method for gauging the reliability of…

Computation and Language · Computer Science 2023-11-23 Chiwei Zhu , Benfeng Xu , Quan Wang , Yongdong Zhang , Zhendong Mao

Recent developments in balancing the usefulness and safety of Large Language Models (LLMs) have raised a critical question: Are mainstream NLP tasks adequately aligned with safety consideration? Our study, focusing on safety-sensitive…

Computation and Language · Computer Science 2024-06-10 Yu Fu , Yufei Li , Wen Xiao , Cong Liu , Yue Dong

Despite the significant progress made in practical applications of aligned language models (LMs), they tend to be overconfident in output answers compared to the corresponding pre-trained LMs. In this work, we systematically evaluate the…

Machine Learning · Computer Science 2023-11-21 Guande He , Peng Cui , Jianfei Chen , Wenbo Hu , Jun Zhu

Large Language Model (LLM) alignment aims to ensure that LLM outputs match with human values. Researchers have demonstrated the severity of alignment problems with a large spectrum of jailbreak techniques that can induce LLMs to produce…

Computation and Language · Computer Science 2024-02-06 Xiaolong Jin , Zhuo Zhang , Xiangyu Zhang

Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on custom…

Computation and Language · Computer Science 2023-10-06 Xiangyu Qi , Yi Zeng , Tinghao Xie , Pin-Yu Chen , Ruoxi Jia , Prateek Mittal , Peter Henderson

Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that…

Computation and Language · Computer Science 2024-09-25 Essa Jan , Nouar AlDahoul , Moiz Ali , Faizan Ahmad , Fareed Zaffar , Yasir Zaki

The proliferation of open-source Large Language Models (LLMs) from various institutions has highlighted the urgent need for comprehensive evaluation methods. However, current evaluation platforms, such as the widely recognized HuggingFace…

Computation and Language · Computer Science 2024-11-01 Fanghua Ye , Mingming Yang , Jianhui Pang , Longyue Wang , Derek F. Wong , Emine Yilmaz , Shuming Shi , Zhaopeng Tu

Advancements in large language models (LLMs) have renewed concerns about AI alignment - the consistency between human and AI goals and values. As various jurisdictions enact legislation on AI safety, the concept of alignment must be defined…

Computers and Society · Computer Science 2025-02-26 Claudia Biancotti , Carolina Camassa , Andrea Coletta , Oliver Giudice , Aldo Glielmo

Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face of jailbreak attacks that modify inputs to induce unsafe outputs. In this paper, we introduce and evaluate a new…

Cryptography and Security · Computer Science 2026-02-19 Jean-Charles Noirot Ferrand , Yohan Beugin , Eric Pauley , Ryan Sheatsley , Patrick McDaniel

Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanisms, which can still be induced to generate unsafe responses,…

Computation and Language · Computer Science 2024-12-18 Weixiang Zhao , Yulin Hu , Zhuojun Li , Yang Deng , Jiahe Guo , Xingyu Sui , Yanyan Zhao , Bing Qin , Tat-Seng Chua , Ting Liu

The safety mechanisms of large language models (LLMs) exhibit notable fragility, as even fine-tuning on datasets without harmful content may still undermine their safety capabilities. Meanwhile, existing safety alignment methods…

Computers and Society · Computer Science 2026-02-03 Guanghao Zhou , Panjia Qiu , Cen Chen , Hongyu Li , Mingyuan Chu , Xin Zhang , Jun Zhou

Large language models (LLMs) often present answers with high apparent confidence despite lacking an explicit mechanism for reasoning about certainty or truth. While existing benchmarks primarily evaluate single-turn accuracy, truthfulness…

Computation and Language · Computer Science 2026-03-05 Mohammadreza Saadat , Steve Nemzer

Many text generation applications require the generated text to be factually consistent with input information. Automatic evaluation of factual consistency is challenging. Previous work has developed various metrics that often depend on…

Computation and Language · Computer Science 2023-05-29 Yuheng Zha , Yichi Yang , Ruichen Li , Zhiting Hu

Studying the robustness of Large Language Models (LLMs) to unsafe behaviors is an important topic of research today. Building safety classification models or guard models, which are fine-tuned models for input/output safety classification…

Computation and Language · Computer Science 2025-07-30 Sowmya Vajjala

Large language models have demonstrated significant potential as the next-generation information access engines. However, their reliability is hindered by issues of hallucination and generating non-factual content. This is particularly…

Computation and Language · Computer Science 2024-10-03 Chao-Wei Huang , Yun-Nung Chen