English
Related papers

Related papers: Poser: Unmasking Alignment Faking LLMs by Manipula…

200 papers

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

Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truthfulness and factuality are thus of great interest. To help users make the right decisions about the information they get, LLMs should not…

Computation and Language · Computer Science 2024-04-03 Chenglei Si , Navita Goyal , Sherry Tongshuang Wu , Chen Zhao , Shi Feng , Hal Daumé , Jordan Boyd-Graber

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…

Computation and Language · Computer Science 2021-08-13 Zi-Yi Dou , Graham Neubig

People are increasingly using technologies equipped with large language models (LLM) to write texts for formal communication, which raises two important questions at the intersection of technology and society: Who do LLMs write like (model…

Computation and Language · Computer Science 2026-01-23 Jinsook Lee , AJ Alvero , Thorsten Joachims , René Kizilcec

Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-conducted alignment…

Computation and Language · Computer Science 2025-09-24 Jiaming Ji , Kaile Wang , Tianyi Qiu , Boyuan Chen , Jiayi Zhou , Changye Li , Hantao Lou , Juntao Dai , Yunhuai Liu , Yaodong Yang

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

Computation and Language · Computer Science 2024-08-05 Bo Zhou , Daniel Geißler , Paul Lukowicz

Alignment faking in large language models presented a demonstration of Claude 3 Opus and Claude 3.5 Sonnet selectively complying with a helpful-only training objective to prevent modification of their behavior outside of training. We expand…

Machine Learning · Computer Science 2025-06-24 Abhay Sheshadri , John Hughes , Julian Michael , Alex Mallen , Arun Jose , Janus , Fabien Roger

The current fascination with large language models, or LLMs, derives from the fact that many users lack the expertise to evaluate the quality of the generated text. LLMs may therefore appear more capable than they actually are. The…

Computation and Language · Computer Science 2024-03-15 Eliza Mik

Large language models optimized with techniques like RLHF have achieved good alignment in being helpful and harmless. However, post-alignment, these language models often exhibit overconfidence, where the expressed confidence does not…

Computation and Language · Computer Science 2024-10-10 Mozhi Zhang , Mianqiu Huang , Rundong Shi , Linsen Guo , Chong Peng , Peng Yan , Yaqian Zhou , Xipeng Qiu

Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where the LLMs' knowledge boundaries are ambiguous. To improve…

Computation and Language · Computer Science 2025-05-26 Boyang Xue , Fei Mi , Qi Zhu , Hongru Wang , Rui Wang , Sheng Wang , Erxin Yu , Xuming Hu , Kam-Fai Wong

Misalignment in Large Language Models (LLMs) arises when model behavior diverges from human expectations and fails to simultaneously satisfy safety, value, and cultural dimensions, which must co-occur in real-world settings to solve a…

Computation and Language · Computer Science 2026-02-13 Usman Naseem , Gautam Siddharth Kashyap , Rafiq Ali , Ebad Shabbir , Sushant Kumar Ray , Abdullah Mohammad , Agrima Seth

Large language models (LLMs) are increasingly used to support scientific work, but it is unclear whether they uphold responsible conduct of research (RCR) norms or help undermine them. We introduce SciIntBench, an adversarial benchmark of…

Cryptography and Security · Computer Science 2026-05-29 Almene De Meran Meguimtsop , Maria Leonor Pacheco , Daniel E. Acuna

Modeling plausible student misconceptions is critical for AI in education. In this work, we examine how large language models (LLMs) reason about misconceptions when generating multiple-choice distractors, a task that requires modeling…

Computation and Language · Computer Science 2026-03-17 Yanick Zengaffinen , Andreas Opedal , Donya Rooein , Kv Aditya Srivatsa , Shashank Sonkar , Mrinmaya Sachan

Large language models (LLMs) are increasingly deployed as conversational assistants in open-domain, multi-turn settings, where users often provide incomplete or ambiguous information. However, existing LLM-focused clarification benchmarks…

Computation and Language · Computer Science 2025-12-25 Sichun Luo , Yi Huang , Mukai Li , Shichang Meng , Fengyuan Liu , Zefa Hu , Junlan Feng , Qi Liu

When large language models (LLMs) are aligned to a specific online community, do they exhibit generalizable behavioral patterns that mirror that community's attitudes and responses to new uncertainty, or are they simply recalling patterns…

Computation and Language · Computer Science 2025-11-25 Patrick Gerard , Aiden Chang , Svitlana Volkova

Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appropriate underlying mechanisms and risking confirmation bias. We introduce a simple,…

Computation and Language · Computer Science 2026-04-01 Zoë Prins , Samuele Punzo , Frank Wildenburg , Giovanni Cinà , Sandro Pezzelle

In everyday conversations, humans can take on different roles and adapt their vocabulary to their chosen roles. We explore whether LLMs can take on, that is impersonate, different roles when they generate text in-context. We ask LLMs to…

Artificial Intelligence · Computer Science 2023-11-28 Leonard Salewski , Stephan Alaniz , Isabel Rio-Torto , Eric Schulz , Zeynep Akata

A prominent weakness of modern language models (LMs) is their tendency to generate factually incorrect text, which hinders their usability. A natural question is whether such factual errors can be detected automatically. Inspired by…

Computation and Language · Computer Science 2023-05-23 Roi Cohen , May Hamri , Mor Geva , Amir Globerson

Large Language Models (LLMs) are widely used for automated code generation, yet their apparent successes often mask a tension between pretraining objectives and alignment choices. While pretraining encourages models to exploit all available…

Software Engineering · Computer Science 2025-12-25 Oussama Ben Sghaier , Kevin Delcourt , Houari Sahraoui

Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks. However, their practical application in high-stake domains, such as fraud and abuse detection, remains an area that requires…

Computation and Language · Computer Science 2024-09-11 Joymallya Chakraborty , Wei Xia , Anirban Majumder , Dan Ma , Walid Chaabene , Naveed Janvekar