English
Related papers

Related papers: Bridging Mechanistic Interpretability and Prompt E…

200 papers

Automatic Short Answer Grading (ASAG) with generative large language models (LLMs) has recently demonstrated strong performance without task-specific fine-tuning, while also enabling the generation of synthetic feedback for educational…

Computation and Language · Computer Science 2026-05-14 Longwei Cong , Sonja Hahn , Sebastian Gombert , Leon Camus , Hendrik Drachsler , Ulf Kroehne

Large Language Models (LLMs) are increasingly used as code assistants, yet their behavior when explicitly asked to generate insecure code remains poorly understood. While prior research has focused on unintended vulnerabilities, this study…

Software Engineering · Computer Science 2025-07-24 Emir Bosnak , Sahand Moslemi , Mayasah Lami , Anil Koyuncu

Large Language Models (LLMs) have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration introduces novel attack surfaces. In this paper, we identify and…

Cryptography and Security · Computer Science 2025-07-23 Yue Li , Xiao Li , Hao Wu , Yue Zhang , Fengyuan Xu , Xiuzhen Cheng , Sheng Zhong

Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) prompting and in-context learning (ICL), the prompts fed to LLMs…

Computation and Language · Computer Science 2023-12-07 Huiqiang Jiang , Qianhui Wu , Chin-Yew Lin , Yuqing Yang , Lili Qiu

As language models achieve increasingly human-like capabilities in conversational text generation, a critical question emerges: to what extent can these systems simulate the characteristics of specific individuals? To evaluate this, we…

Computation and Language · Computer Science 2025-06-04 Quan Shi , Carlos E. Jimenez , Stephen Dong , Brian Seo , Caden Yao , Adam Kelch , Karthik Narasimhan

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 propose SelfControl, an inference-time model control method utilizing gradients to control the behavior of large language models (LLMs) without explicit human annotations. Given a desired behavior expressed in a natural language suffix…

Computation and Language · Computer Science 2024-10-15 Min Cai , Yuchen Zhang , Shichang Zhang , Fan Yin , Dan Zhang , Difan Zou , Yisong Yue , Ziniu Hu

Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompting and activation steering expose *different*, architecture-dependent vulnerability…

Artificial Intelligence · Computer Science 2026-04-15 Wenkai Li , Fan Yang , Shaunak A. Mehta , Koichi Onoue

Large Language Models (LLMs) are rapidly surpassing human knowledge in many domains. While improving these models traditionally relies on costly human data, recent self-rewarding mechanisms (Yuan et al., 2024) have shown that LLMs can…

Computation and Language · Computer Science 2024-07-31 Tianhao Wu , Weizhe Yuan , Olga Golovneva , Jing Xu , Yuandong Tian , Jiantao Jiao , Jason Weston , Sainbayar Sukhbaatar

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal…

Machine Learning · Computer Science 2026-03-17 Ming Wen , Kun Yang , Xin Chen , Jingyu Zhang , Dingding Han , Shiwen Cui , Yuedong Xu

Large Language Models (LLMs) often generate substantively relevant content but fail to adhere to formal constraints, leading to outputs that are conceptually correct but procedurally flawed. Traditional prompt refinement approaches focus on…

Artificial Intelligence · Computer Science 2026-01-08 Alberto Purpura , Li Wang , Sahil Badyal , Eugenio Beaufrand , Adam Faulkner

Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themselves as judges, leading to high computational costs and…

Computation and Language · Computer Science 2024-11-28 Shijian Deng , Wentian Zhao , Yu-Jhe Li , Kun Wan , Daniel Miranda , Ajinkya Kale , Yapeng Tian

Hallucination remains a key obstacle to the reliable deployment of large language models (LLMs) in real-world question answering tasks. A widely adopted strategy to detect hallucination, known as self-assessment, relies on the model's own…

Artificial Intelligence · Computer Science 2025-06-04 Jinyuan Luo , Zhen Fang , Yixuan Li , Seongheon Park , Ling Chen

Large language models (LLMs) are increasingly explored as general-purpose reasoners, particularly in agentic contexts. However, their outputs remain prone to mathematical and logical errors. This is especially challenging in open-ended…

Artificial Intelligence · Computer Science 2025-05-30 Agnieszka Mensfelt , Kostas Stathis , Vince Trencsenyi

This study sheds light on the imperative need to bolster safety and privacy measures in large language models (LLMs), such as GPT-4 and LLaMA-2, by identifying and mitigating their vulnerabilities through explainable analysis of prompt…

Cryptography and Security · Computer Science 2024-07-18 Dong Shu , Mingyu Jin , Tianle Chen , Chong Zhang , Yongfeng Zhang

Large Language Models~(LLMs) are prone to hallucinations, and Retrieval-Augmented Generation (RAG) helps mitigate this, but at a high computational cost while risking misinformation. Adaptive retrieval aims to retrieve only when necessary,…

The groundbreaking capabilities of Large Language Models (LLMs) offer new opportunities for enhancing human-computer interaction through emotion-adaptive Artificial Intelligence (AI). However, deliberately controlling the sentiment in these…

Computation and Language · Computer Science 2026-02-09 Kerstin Sahler , Sophie Jentzsch

Large language models (LLMs) are increasingly applied to sequential decision-making through in-context learning (ICL), yet their effectiveness is highly sensitive to prompt quality. Effective prompts should meet three principles: focus on…

Artificial Intelligence · Computer Science 2025-11-19 Ruomeng Ding , Wei Cheng , Minglai Shao , Chen Zhao

Recent developments in text classification using Large Language Models (LLMs) in the social sciences suggest that costs can be cut significantly, while performance can sometimes rival existing computational methods. However, with a wide…

Computation and Language · Computer Science 2026-03-27 Erkan Gunes , Christoffer Florczak , Tevfik Murat Yildirim

Persona prompting has been widely adopted to steer large language models (LLMs) behavior and improve their instruction performance by assigning specific characters. However, identifying an optimal persona is time-consuming, and its impact…

Computation and Language · Computer Science 2026-04-13 Jihwan Oh , Soowon Oh , Murad Aghazada , Minchan Jeong , Sungnyun Kim , Se-Young Yun