English
Related papers

Related papers: Mind the Performance Gap: Capability-Behavior Trad…

200 papers

Personality manipulation in large language models (LLMs) is increasingly applied in customer service and agentic scenarios, yet its mechanisms and trade-offs remain unclear. We present a systematic study of personality control using the Big…

Computation and Language · Computer Science 2025-09-08 Gunmay Handa , Zekun Wu , Adriano Koshiyama , Philip Treleaven

Large language models (LLMs) can still be jailbroken into producing harmful outputs despite safety alignment. Existing attacks show this vulnerability, but not the internal mechanisms that cause it. This study asks whether jailbreak success…

Computation and Language · Computer Science 2026-04-28 Nilanjana Das , Manas Gaur

Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by intervening on token representations without costly updates to…

Computation and Language · Computer Science 2025-07-10 Duy Nguyen , Archiki Prasad , Elias Stengel-Eskin , Mohit Bansal

Large language models (LLMs) exhibit distinct and consistent personalities that greatly impact trust and engagement. While this means that personality frameworks would be highly valuable tools to characterize and control LLMs' behavior,…

Computation and Language · Computer Science 2026-01-19 Michel Frising , Daniel Balcells

Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and…

Computation and Language · Computer Science 2025-10-02 Zifeng Cheng , Jinwei Gan , Zhiwei Jiang , Cong Wang , Yafeng Yin , Xiang Luo , Yuchen Fu , Qing Gu

Parameter Efficient Finetuning (PEFT) has emerged as a viable solution for improving the performance of Large Language Models (LLMs) without requiring massive resources and compute. Prior work on multilingual evaluation has shown that there…

Computation and Language · Computer Science 2024-07-23 Divyanshu Aggarwal , Ashutosh Sathe , Ishaan Watts , Sunayana Sitaram

Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed as a precise, interpretable, and potentially…

Machine Learning · Computer Science 2026-02-17 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Y. Rogov , Ivan Oseledets , Elena Tutubalina

Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability are well-documented, its safety implications remain underexplored. In this work,…

Cryptography and Security · Computer Science 2026-03-26 Yuxiao Li , Alina Fastowski , Efstratios Zaradoukas , Bardh Prenkaj , Gjergji Kasneci

This paper investigates how prompt engineering techniques impact both accuracy and confidence elicitation in Large Language Models (LLMs) applied to medical contexts. Using a stratified dataset of Persian board exam questions across…

Computers and Society · Computer Science 2025-06-03 Nariman Naderi , Zahra Atf , Peter R Lewis , Aref Mahjoub far , Seyed Amir Ahmad Safavi-Naini , Ali Soroush

We present Fusion Steering, an activation steering methodology that improves factual accuracy in large language models (LLMs) for question-answering (QA) tasks. This approach introduces flexible steering configurations, including full-layer…

Computation and Language · Computer Science 2025-05-29 Waldemar Chang , Alhassan Yasin

Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses. Understanding their internal states is crucial for understanding their successes, diagnosing their failures,…

Computation and Language · Computer Science 2025-02-24 Xuansheng Wu , Jiayi Yuan , Wenlin Yao , Xiaoming Zhai , Ninghao Liu

Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the…

Computation and Language · Computer Science 2025-12-04 Kylie L. Anglin , Stephanie Milan , Brittney Hernandez , Claudia Ventura

Large Language Models (LLMs) exhibit impressive performance across diverse domains but often suffer from overconfidence, limiting their reliability in critical applications. We propose SteerConf, a novel framework that systematically steers…

Computation and Language · Computer Science 2025-05-27 Ziang Zhou , Tianyuan Jin , Jieming Shi , Qing Li

Deterministically controlling the target generation language of large multilingual language models (LLMs) remains a fundamental challenge, particularly in zero-shot settings where neither explicit language prompts nor fine-tuning are…

Computation and Language · Computer Science 2025-10-17 Cheng-Ting Chou , George Liu , Jessica Sun , Cole Blondin , Kevin Zhu , Vasu Sharma , Sean O'Brien

Existing open-source helpfulness preference datasets do not specify what makes some responses more helpful and others less so. Models trained on these datasets can incidentally learn to model dataset artifacts (e.g. preferring longer but…

Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context few-shot learning. To investigate this few-shot dilemma, we…

Computation and Language · Computer Science 2025-09-17 Yongjian Tang , Doruk Tuncel , Christian Koerner , Thomas Runkler

Effective and reliable control over large language model (LLM) behavior is a significant challenge. While activation steering methods, which add steering vectors to a model's hidden states, are a promising approach, existing techniques…

Machine Learning · Computer Science 2025-04-03 Samuel Soo , Chen Guang , Wesley Teng , Chandrasekaran Balaganesh , Tan Guoxian , Yan Ming

As large language models (LLMs) continue to improve and see further integration into software systems, so does the need to understand the conditions in which they will perform. We contribute a statistical framework for understanding the…

Machine Learning · Computer Science 2026-03-31 Andrew Lauziere , Jonathan Daugherty , Taisa Kushner

Large Language Models (LLMs) have attracted significant attention due to their human-like language understanding and generation capabilities, as well as their applicability across various domains. These models, characterized by their…

Machine Learning · Computer Science 2024-11-14 Kazuki Fujii , Taishi Nakamura , Rio Yokota

We introduce SteeringSafety, a systematic framework for evaluating representation steering methods across seven safety perspectives spanning 17 datasets. While prior work highlights general capabilities of representation steering, we…

Artificial Intelligence · Computer Science 2025-10-17 Vincent Siu , Nicholas Crispino , David Park , Nathan W. Henry , Zhun Wang , Yang Liu , Dawn Song , Chenguang Wang