English
Related papers

Related papers: Are Aligned Large Language Models Still Misaligned…

200 papers

Self-destructive behaviors are linked to complex psychological states and can be challenging to diagnose. These behaviors may be even harder to identify within subcultural groups due to their unique expressions. As large language models…

Computation and Language · Computer Science 2026-05-26 Peng Wang , Xilin Tao , Siyi Yao , Jiageng Wu , Yuntao Zou , Zhuotao Tian , Libo Qin , Dagang Li

Large language models (LLMs) demonstrate considerable potential in various natural language tasks but face significant challenges in mathematical reasoning, particularly in executing precise, multi-step logic. However, current evaluation…

Computation and Language · Computer Science 2025-05-22 Tiasa Singha Roy , Aditeya Baral , Ayush Rajesh Jhaveri , Yusuf Baig

Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning yet poorly understood phenomenon, in part because current diagnostic tools remain…

Artificial Intelligence · Computer Science 2026-04-29 Inderjeet Nair , Jie Ruan , Lu Wang

Open Large Language Model (LLM) benchmarks, such as HELM and BIG-Bench, provide standardized and transparent evaluation protocols that support comparative analysis, reproducibility, and systematic progress tracking in Language Model (LM)…

Computation and Language · Computer Science 2026-01-08 Md. Najib Hasan , Md Mahadi Hassan Sibat , Mohammad Fakhruddin Babar , Souvika Sarkar , Monowar Hasan , Santu Karmaker

Language models (LMs) are increasingly used as simulacra for people, yet their ability to match the distribution of views of a specific demographic group and be \textit{distributionally aligned} remains uncertain. This notion of…

Computation and Language · Computer Science 2024-11-11 Nicole Meister , Carlos Guestrin , Tatsunori Hashimoto

The ability to follow instructions is crucial for Large Language Models (LLMs) to handle various real-world applications. Existing benchmarks primarily focus on evaluating pure response quality, rather than assessing whether the response…

Computation and Language · Computer Science 2024-06-06 Yuxin Jiang , Yufei Wang , Xingshan Zeng , Wanjun Zhong , Liangyou Li , Fei Mi , Lifeng Shang , Xin Jiang , Qun Liu , Wei Wang

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying…

Cryptography and Security · Computer Science 2024-06-11 Xiangyu Qi , Ashwinee Panda , Kaifeng Lyu , Xiao Ma , Subhrajit Roy , Ahmad Beirami , Prateek Mittal , Peter Henderson

Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the…

Computation and Language · Computer Science 2025-06-23 Kathleen C. Fraser , Hillary Dawkins , Isar Nejadgholi , Svetlana Kiritchenko

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

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Artificial Intelligence · Computer Science 2025-02-18 Yingshui Tan , Yilei Jiang , Yanshi Li , Jiaheng Liu , Xingyuan Bu , Wenbo Su , Xiangyu Yue , Xiaoyong Zhu , Bo Zheng

Large Language Models (LLMs) achieve competitive results compared to human experts in medical examinations. However, it remains a challenge to apply LLMs to complex clinical decision-making, which requires a deep understanding of medical…

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

Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment. However, aligning LLMs remains challenging due to the inherent…

Safety concerns of Multimodal large language models (MLLMs) have gradually become an important problem in various applications. Surprisingly, previous works indicate a counterintuitive phenomenon that using textual unlearning to align MLLMs…

Cryptography and Security · Computer Science 2025-05-20 Xuhao Hu , Dongrui Liu , Hao Li , Xuanjing Huang , Jing Shao

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

The rapid advancement of large language models (LLMs) has not been matched by their evaluation in low-resource languages, especially Southeast Asian languages like Lao. To fill this gap, we introduce \textbf{LaoBench}, the first…

Computation and Language · Computer Science 2026-04-16 Jian Gao , Richeng Xuan , Zhaolu Kang , Dingshi Liao , Wenxin Huang , Zongmou Huang , Yangdi Xu , Bowen Qin , Zheqi He , Xi Yang , Changjin Li , Yonghua Lin

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and…

Machine Learning · Computer Science 2026-02-10 Kaustubh Ponkshe , Shaan Shah , Raghav Singhal , Praneeth Vepakomma

Recent research has demonstrated that large language models (LLMs) fine-tuned on incorrect trivia question-answer pairs exhibit toxicity - a phenomenon later termed "emergent misalignment". Moreover, research has shown that LLMs possess…

Computation and Language · Computer Science 2026-02-17 Laurène Vaugrante , Anietta Weckauff , Thilo Hagendorff

Large language models (LLMs) are increasingly applied in financial scenarios. However, they may produce harmful outputs, including facilitating illegal activities or unethical behavior, posing serious compliance risks. To systematically…

Computation and Language · Computer Science 2026-05-04 Yutao Hou , Yihan Jiang , Yuhan Xie , Jian Yang , Liwen Zhang , Hailiang Huang , Guanhua Chen , Yun Chen

Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that…

Computation and Language · Computer Science 2026-04-13 Hadas Orgad , Boyi Wei , Kaden Zheng , Martin Wattenberg , Peter Henderson , Seraphina Goldfarb-Tarrant , Yonatan Belinkov