English
Related papers

Related papers: Breaking the Mirror: Activation-Based Mitigation o…

200 papers

Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives simultaneously. Existing methods predominantly rely on static preference weight…

Machine Learning · Computer Science 2026-04-28 Wenzhe Xu , Biao Liu , Yiyang Sun , Xin Geng , Ning Xu

Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who…

Computation and Language · Computer Science 2025-03-05 Xinru Lin , Luyang Li

Current approaches for strengthening LLM reasoning tend to introduce a training bias toward human-like reasoning trajectories. In step-wise preference optimization, in particular, dependence on human or higher-capacity model annotations for…

Computation and Language · Computer Science 2026-02-03 Junjie Lu , Yuliang Liu , Chaofeng Qu , Wei Shen , Zhouhan Lin , Chuheng Zhang , Min Xu

Large language models (LLMs) have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produce responses that better align with the preferences of those…

Computation and Language · Computer Science 2025-08-12 Hannah Cyberey , David Evans

LLM-based Automatic Prompt Optimization, which typically utilizes LLMs as Prompt Optimizers to self-reflect and refine prompts, has shown promising performance in recent studies. Despite the success, the underlying mechanism of this…

Computation and Language · Computer Science 2024-02-06 Ruotian Ma , Xiaolei Wang , Xin Zhou , Jian Li , Nan Du , Tao Gui , Qi Zhang , Xuanjing Huang

Vision Language Models (VLMs) have demonstrated impressive capabilities in integrating visual and textual information for understanding and reasoning, but remain highly vulnerable to adversarial attacks. While activation steering has…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Sihao Wu , Gaojie Jin , Wei Huang , Jianhong Wang , Xiaowei Huang

With the onset of large language models (LLMs), the performance of artificial intelligence (AI) models is becoming increasingly multi-dimensional. Accordingly, there have been several large, multi-dimensional evaluation frameworks put…

Human-Computer Interaction · Computer Science 2025-06-05 Sean Steinle

As LLMs rapidly saturate existing benchmarks, automated benchmark creation using LLMs (LLM-as-a-benchmark) -- where a model generates test inputs (LLM-as-a-testset) and evaluates outputs (LLM-as-an-evaluator) -- has gained traction as a…

Computation and Language · Computer Science 2026-05-27 Wenda Xu , Sweta Agrawal , Vilém Zouhar , Markus Freitag , Daniel Deutsch

Can large language models (LLMs) learn a decision maker's preferences from observed choices and generate preference-consistent recommendations in new situations? We propose a portable Simulate-Recommend-Evaluate framework that tests…

General Economics · Economics 2026-04-08 Jeongbin Kim , Matthew Kovach , Kyu-Min Lee , Euncheol Shin , Hector Tzavellas

LLM-based auto-annotators have become a key component of the LLM development process due to their cost-effectiveness and scalability compared to human-based evaluation. However, these auto-annotators can introduce biases that are hard to…

Machine Learning · Computer Science 2025-03-11 Yann Dubois , Balázs Galambosi , Percy Liang , Tatsunori B. Hashimoto

We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour on politically sensitive topics without retraining. We replace fragile pattern-based refusal detection…

Computation and Language · Computer Science 2026-02-25 Iker García-Ferrero , David Montero , Roman Orus

Recently, large vision-language models (LVLMs) have emerged as the preferred tools for judging text-image alignment, yet their robustness along the visual modality remains underexplored. This work is the first study to address a key…

Computation and Language · Computer Science 2025-11-18 Yerin Hwang , Dongryeol Lee , Kyungmin Min , Taegwan Kang , Yong-il Kim , Kyomin Jung

Large language models demonstrate impressive reasoning abilities but struggle to provide personalized content due to their lack of individual user preference information. Existing methods, such as in-context learning and parameter-efficient…

Computation and Language · Computer Science 2024-12-10 Sumuk Shashidhar , Abhinav Chinta , Vaibhav Sahai , Dilek Hakkani-Tür

Recent advancements in large language models (LLMs) have resulted in increasingly anthropomorphic language concerning the ability of LLMs to reason. Whether reasoning in LLMs should be understood to be inherently different is, however,…

Machine Learning · Computer Science 2025-07-28 Bertram Højer , Oliver Jarvis , Stefan Heinrich

Large Language Models (LLMs) have become pivotal in advancing natural language processing, yet their potential to perpetuate biases poses significant concerns. This paper introduces a new framework employing Direct Preference Optimization…

Computation and Language · Computer Science 2024-07-22 Ahmed Allam

Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs), but the performance is still underwhelming due to too much noisy preference data yielded in the loop. To combat…

Computation and Language · Computer Science 2024-09-18 Jianing Wang , Yang Zhou , Xiaocheng Zhang , Mengjiao Bao , Peng Yan

Precise control over language model generation is vital for ensuring both safety and reliability. Although prompt engineering and steering are commonly used to intervene in model behaviors, the vast number of parameters in models often…

Computation and Language · Computer Science 2025-06-04 Mengru Wang , Ziwen Xu , Shengyu Mao , Shumin Deng , Zhaopeng Tu , Huajun Chen , Ningyu Zhang

Steering Large Language Models (LLMs) through activation interventions has emerged as a lightweight alternative to fine-tuning for alignment and personalization. Recent work on Bi-directional Preference Optimization (BiPO) shows that dense…

Artificial Intelligence · Computer Science 2026-01-14 Abdelaziz Bounhar , Rania Hossam Elmohamady Elbadry , Hadi Abdine , Preslav Nakov , Michalis Vazirgiannis , Guokan Shang

Large language models (LLMs) are currently aligned using techniques such as reinforcement learning from human feedback (RLHF). However, these methods use scalar rewards that can only reflect user preferences on average. Pluralistic…

Computation and Language · Computer Science 2025-08-13 Jadie Adams , Brian Hu , Emily Veenhuis , David Joy , Bharadwaj Ravichandran , Aaron Bray , Anthony Hoogs , Arslan Basharat

Large language models (LLMs) are known to be sensitive to input phrasing, but the mechanisms by which semantic cues shape reasoning remain poorly understood. We investigate this phenomenon in the context of comparative math problems with…

Computation and Language · Computer Science 2025-06-05 Mohammadamin Shafiei , Hamidreza Saffari , Nafise Sadat Moosavi