English
Related papers

Related papers: Emergently Misaligned Language Models Show Behavio…

200 papers

Large Language Models (LLMs) have shown great potential in Natural Language Processing (NLP) tasks. However, recent literature reveals that LLMs generate nonfactual responses intermittently, which impedes the LLMs' reliability for further…

Computation and Language · Computer Science 2024-03-22 Yukun Zhao , Lingyong Yan , Weiwei Sun , Guoliang Xing , Chong Meng , Shuaiqiang Wang , Zhicong Cheng , Zhaochun Ren , Dawei Yin

Recently, Large Language Models (LLMs) have shown impressive language capabilities. While most of the existing LLMs have very unbalanced performance across different languages, multilingual alignment based on translation parallel data is an…

Computation and Language · Computer Science 2024-06-19 Shimao Zhang , Changjiang Gao , Wenhao Zhu , Jiajun Chen , Xin Huang , Xue Han , Junlan Feng , Chao Deng , Shujian Huang

Advances in Large Language Models (LLMs) have enabled a new class of self-evolving agents that autonomously improve through interaction with the environment, demonstrating strong capabilities. However, self-evolution also introduces novel…

Artificial Intelligence · Computer Science 2026-03-10 Shuai Shao , Qihan Ren , Chen Qian , Boyi Wei , Dadi Guo , Jingyi Yang , Xinhao Song , Linfeng Zhang , Weinan Zhang , Dongrui Liu , Jing Shao

The conformity effect describes the tendency of individuals to align their responses with the majority. Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and…

Computation and Language · Computer Science 2025-05-27 Xiaochen Zhu , Caiqi Zhang , Tom Stafford , Nigel Collier , Andreas Vlachos

Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where outputs may be reused as context. In this work, we…

Computation and Language · Computer Science 2026-03-18 Tianyi Zhou , Johanne Medina , Sanjay Chawla

When large language models are aligned via supervised fine-tuning, they may encounter new factual information that was not acquired through pre-training. It is often conjectured that this can teach the model the behavior of hallucinating…

Computation and Language · Computer Science 2024-10-02 Zorik Gekhman , Gal Yona , Roee Aharoni , Matan Eyal , Amir Feder , Roi Reichart , Jonathan Herzig

As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents' ability to produce harmful outputs or follow malicious instructions, it remains unclear how likely…

Large Language Models (LLMs) have demonstrated remarkable capabilities in performing complex cognitive tasks. However, their complexity and lack of transparency have raised several trustworthiness concerns, including the propagation of…

Machine Learning · Computer Science 2023-11-07 Satyapriya Krishna

Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing safety alignment, converting the outcomes of stronger…

Computation and Language · Computer Science 2024-06-07 Zhanhui Zhou , Jie Liu , Zhichen Dong , Jiaheng Liu , Chao Yang , Wanli Ouyang , Yu Qiao

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Computation and Language · Computer Science 2025-08-07 Siddhant Panpatil , Hiskias Dingeto , Haon Park

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Computation and Language · Computer Science 2023-08-28 Aibek Bekbayev , Sungbae Chun , Yerzat Dulat , James Yamazaki

Ashery et al. recently argue that large language models (LLMs), when paired to play a classic "naming game," spontaneously develop linguistic conventions reminiscent of human social norms. Here, we show that their results are better…

Computation and Language · Computer Science 2025-06-02 Christopher Barrie , Petter Törnberg

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

As large language models (LLMs) gain popularity, their vulnerability to adversarial attacks emerges as a primary concern. While fine-tuning models on domain-specific datasets is often employed to improve model performance, it can…

Computation and Language · Computer Science 2026-02-24 Punya Syon Pandey , Samuel Simko , Kellin Pelrine , Zhijing Jin

Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Therefore, it is of great importance to evaluate their emerging abilities. In this study, we show that LLMs,…

Computation and Language · Computer Science 2023-10-10 Thilo Hagendorff , Sarah Fabi

Large Language Models (LLMs) have been transformative. They are pre-trained foundational models that are self-supervised and can be adapted with fine tuning to a wide range of natural language tasks, each of which previously would have…

Computation and Language · Computer Science 2023-02-22 Terrence Sejnowski

Earlier research has shown that metaphors influence human's decision making, which raises the question of whether metaphors also influence large language models (LLMs)' reasoning pathways, considering their training data contain a large…

Computation and Language · Computer Science 2026-01-13 Zhibo Hu , Chen Wang , Yanfeng Shu , Hye-young Paik , Liming Zhu

A potential concern when simulating populations of large language models (LLMs) is data contamination, i.e. the possibility that training data may shape outcomes in unintended ways. While this concern is important and may hinder certain…

Computation and Language · Computer Science 2025-06-24 Ariel Flint Ashery , Luca Maria Aiello , Andrea Baronchelli

Lifelong multimodal agents must continuously adapt to new tasks through post-training, but this creates a fundamental tension between acquiring capabilities and preserving safety alignment. We demonstrate that fine-tuning aligned…

Artificial Intelligence · Computer Science 2026-03-17 Idhant Gulati , Shivam Raval

Large Language Models (LLMs) have revolutionized numerous applications, making them an integral part of our digital ecosystem. However, their reliability becomes critical, especially when these models are exposed to misinformation. We…

Computation and Language · Computer Science 2024-09-12 Alina Fastowski , Gjergji Kasneci