English
Related papers

Related papers: Steering Language Models With Activation Engineeri…

200 papers

This Monte Carlo simulation examines how prompt engineering strategies shape the quality of large language model (LLM)--generated personality assessment items within the AI-GENIE framework for generative psychometrics. Item pools targeting…

Artificial Intelligence · Computer Science 2026-03-18 Lara Lee Russell-Lasalandra , Hudson Golino

Large language models' behavior is often shaped by instructions such as system prompts, refusal boundaries, privacy constraints, and tool-use rules that must hold at inference time. Yet in practice these constraints can be violated under…

Computation and Language · Computer Science 2026-03-27 Vitoria Guardieiro , Avishree Khare , Adam Stein , Eric Wong

Prompt engineering is a critical technique in the field of natural language processing that involves designing and optimizing the prompts used to input information into models, aiming to enhance their performance on specific tasks. With the…

Transformer-based language models excel in NLP tasks, but fine-grained control remains challenging. This paper explores methods for manipulating transformer models through principled interventions at three levels: prompts, activations, and…

Computation and Language · Computer Science 2025-09-08 Faruk Alpay , Taylan Alpay

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

Prompt engineering is still the primary way for users of generative text-to-image models to manipulate generated images in a targeted way. Based on treating the model as a continuous function and by passing gradients between the image space…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Niklas Deckers , Julia Peters , Martin Potthast

While Large Language Models (LLMs) are being quickly adapted to many domains, including healthcare, their strengths and pitfalls remain under-explored. In our study, we examine the effects of prompt engineering to guide Large Language…

Computation and Language · Computer Science 2024-09-04 Daniil Filienko , Yinzhou Wang , Caroline El Jazmi , Serena Xie , Trevor Cohen , Martine De Cock , Weichao Yuwen

Prompt engineering has made significant contributions to the era of large language models, yet its effectiveness depends on the skills of a prompt author. This paper introduces $\textit{iPrOp}$, a novel interactive prompt optimization…

Computation and Language · Computer Science 2025-06-30 Jiahui Li , Roman Klinger

We introduce InstructABSA, an instruction learning paradigm for Aspect-Based Sentiment Analysis (ABSA) subtasks. Our method introduces positive, negative, and neutral examples to each training sample, and instruction tune the model…

Computation and Language · Computer Science 2023-11-14 Kevin Scaria , Himanshu Gupta , Siddharth Goyal , Saurabh Arjun Sawant , Swaroop Mishra , Chitta Baral

Recent advances in large language models (LLMs) have led to their popularity across multiple use-cases. However, prompt engineering, the process for optimally utilizing such models, remains approximation-driven and subjective. Most of the…

Computational Complexity · Computer Science 2025-04-29 Aashutosh Nema , Samaksh Gulati , Evangelos Giakoumakis , Bipana Thapaliya

The performance of large language models (LLMs) is significantly influenced by the quality of the prompts provided. In response, researchers have developed enormous prompt engineering strategies aimed at modifying the prompt text to enhance…

Computation and Language · Computer Science 2024-10-23 Zhiyuan He , Huiqiang Jiang , Zilong Wang , Yuqing Yang , Luna Qiu , Lili Qiu

Code translation is a crucial process in software development and migration projects, enabling interoperability between different programming languages and enhancing software adaptability and thus longevity. Traditional automated…

Artificial Intelligence · Computer Science 2025-07-23 Shreya Saxena , Siva Prasad , Zishan Ahmad , Vishal Vaddina

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial…

Computation and Language · Computer Science 2024-07-31 Yuanpu Cao , Tianrong Zhang , Bochuan Cao , Ziyi Yin , Lu Lin , Fenglong Ma , Jinghui Chen

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…

Computation and Language · Computer Science 2025-01-23 Jingyuan Yang , Rongjun Li , Weixuan Wang , Ziyu Zhou , Zhiyong Feng , Wei Peng

Active Test-Time Adaptation (ATTA) improves model robustness under domain shift by selectively querying human annotations at deployment, but existing methods use heuristic uncertainty measures and suffer from low data selection efficiency,…

Machine Learning · Computer Science 2025-10-01 Tingyu Shi , Fan Lyu , Shaoliang Peng

The ReAct (Reasoning + Action) capability in large language models (LLMs) has become the foundation of modern agentic systems. Recent LLMs, such as DeepSeek-R1 and OpenAI o1/o3, exemplify this by emphasizing reasoning through the generation…

Artificial Intelligence · Computer Science 2025-05-20 Mrinal Rawat , Ambuje Gupta , Rushil Goomer , Alessandro Di Bari , Neha Gupta , Roberto Pieraccini

Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety. Machine unlearning seeks to remove the influence of a targeted forget set while preserving model…

Language Agent could be endowed with different mechanisms for autonomous task accomplishment. Current agents typically rely on fixed mechanisms or a set of mechanisms activated in a predefined order, limiting their adaptation to varied…

Computation and Language · Computer Science 2024-12-03 Ziyang Huang , Jun Zhao , Kang Liu

While state-of-the-art language models have achieved impressive results, they remain susceptible to inference-time adversarial attacks, such as adversarial prompts generated by red teams arXiv:2209.07858. One approach proposed to improve…

Computation and Language · Computer Science 2024-01-12 Steffi Chern , Zhen Fan , Andy Liu

Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizations. To better…

Computation and Language · Computer Science 2026-03-02 Constanza Fierro , Fabien Roger