English
Related papers

Related papers: The Alignment Floor: How Persona Customization Bre…

200 papers

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

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

Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called…

Computation and Language · Computer Science 2026-01-21 Xuhao Hu , Peng Wang , Xiaoya Lu , Dongrui Liu , Xuanjing Huang , Jing Shao

Sycophancy, an excessive tendency of AI models to agree with user input at the expense of factual accuracy or in contradiction of visual evidence, poses a critical and underexplored challenge for multimodal large language models (MLLMs).…

Artificial Intelligence · Computer Science 2025-12-23 A. B. M. Ashikur Rahman , Saeed Anwar , Muhammad Usman , Irfan Ahmad , Ajmal Mian

Harnessing the power of LLMs requires a delicate dance between being helpful and harmless. This creates a fundamental tension between two competing challenges: vulnerability to adversarial attacks that elicit unsafe content, and a tendency…

Despite their widespread use in fact-checking, moderation, and high-stakes decision-making, large language models (LLMs) remain poorly understood as judges of truth. This study presents the largest evaluation to date of LLMs' veracity…

Computation and Language · Computer Science 2025-09-30 Emilio Barkett , Olivia Long , Madhavendra Thakur

Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed, however, that the conventional alignment process fails to…

Computation and Language · Computer Science 2024-05-03 Sheng-Chieh Lin , Luyu Gao , Barlas Oguz , Wenhan Xiong , Jimmy Lin , Wen-tau Yih , Xilun Chen

While Large Language Models (LLMs) are widely documented to be sensitive to minor prompt perturbations and prone to sycophantic alignment, their robustness in consequential, rule-bound decision-making remains under-explored. We uncover a…

Artificial Intelligence · Computer Science 2026-04-07 Jon Chun , Katherine Elkins

As large language models (LLMs) demonstrate increasingly advanced capabilities, aligning their behaviors with human values and preferences becomes crucial for their wide adoption. While previous research focuses on general alignment to…

Computation and Language · Computer Science 2024-12-17 Shujin Wu , May Fung , Cheng Qian , Jeonghwan Kim , Dilek Hakkani-Tur , Heng Ji

Recent advances enable Large Language Models (LLMs) to generate AI personas, yet their lack of deep contextual, cultural, and emotional understanding poses a significant limitation. This study quantitatively compared human responses with…

Computers and Society · Computer Science 2025-12-03 Tabia Tanzin Prama , Christopher M. Danforth , Peter Sheridan Dodds

As Large Language Models (LLMs) continue to gain popularity due to their human-like traits and the intimacy they offer to users, their societal impact inevitably expands. This leads to the rising necessity for comprehensive studies to fully…

Artificial Intelligence · Computer Science 2025-01-07 Bojana Bodroza , Bojana M. Dinic , Ljubisa Bojic

Fine-tuning large language models (LLMs) on narrowly misaligned data generalizes to broadly misaligned behavior, a phenomenon termed emergent misalignment (EM). While prior work has found a correlation between harmful behavior and…

Artificial Intelligence · Computer Science 2026-05-01 Anietta Weckauff , Yuchen Zhang , Maksym Andriushchenko

Large Language Models (LLMs) have shown remarkable progress, but their real-world application necessitates reliable calibration. This study conducts a comprehensive analysis of calibration degradation of LLMs across four dimensions: models,…

Computation and Language · Computer Science 2025-02-11 Hongseok Oh , Wonseok Hwang

Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psychology's focus on mental illness: necessary but incomplete.…

Collaborative problem solving and learning are shaped by who or what is on the team. As large language models (LLMs) increasingly function as collaborators rather than tools, a key question is whether AI teammates can be aligned to express…

Human-Computer Interaction · Computer Science 2026-03-03 Mohammad Amin Samadi , Nia Nixon

Audio Language Models (ALMs) have recently shown strong capabilities in unified reasoning over speech, sound, and natural language; yet they inherit behavioral issues observed in Large Language Models, including sycophancy--the tendency to…

This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across…

Computation and Language · Computer Science 2025-06-03 Gracjan Góral , Emilia Wiśnios , Piotr Sankowski , Paweł Budzianowski

To assist users in complex tasks, LLMs generate plans: step-by-step instructions towards a goal. While alignment methods aim to ensure LLM plans are helpful, they train (RLHF) or evaluate (ChatbotArena) on what users prefer, assuming this…

Applications based on large language models (LLMs), such as multi-agent simulations, require population diversity among agents. We identify a pervasive failure mode we term \emph{Persona Collapse}: agents each assigned a distinct profile…

Computation and Language · Computer Science 2026-04-28 Yunze Xiao , Vivienne J. Zhang , Chenghao Yang , Ningshan Ma , Weihao Xuan , Jen-tse Huang

Background Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains understudied. Prior assessments focused on neutral conditions, overlooking vulnerabilities…

Computation and Language · Computer Science 2026-01-16 Vahideh Zolfaghari