Related papers: ExpertSteer: Intervening in LLMs through Expert Kn…
As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important. Existing behavioral control methods face significant limitations:…
Automated unit test generation using large language models (LLMs) holds great promise but often struggles with generating tests that are both correct and maintainable in real-world projects. This paper presents KTester, a novel framework…
The complementary potential of Large Language Models (LLM) assumes off-the-shelf LLMs have heterogeneous expertise in a wide range of domains and tasks so that an ensemble of LLMs can achieve consistently better performance. Existing…
Model editing aims to precisely alter the behaviors of large language models (LLMs) in relation to specific knowledge, while leaving unrelated knowledge intact. This approach has proven effective in addressing issues of hallucination and…
Multimodal LLMs (MLLMs) have reached remarkable levels of proficiency in understanding multimodal inputs. However, understanding and interpreting the behavior of such complex models is a challenging task, not to mention the dynamic shifts…
As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable use. Recently, activation steering has emerged as an…
Engineering safety-critical systems such as medical devices and digital health intervention systems is complex, where long-term engagement with subject-matter experts (SMEs) is needed to capture the systems' expected behaviour. In this…
We conduct the first empirical study on using knowledge transfer to improve the generalization ability of large language models (LLMs) in software engineering tasks, which often require LLMs to generalize beyond their training data. Our…
Large language models (LLMs) with billions of parameters exhibit in-context learning abilities, enabling few-shot learning on tasks that the model was not specifically trained for. Traditional models achieve breakthrough performance on…
Prompt engineering has emerged as an indispensable technique for extending the capabilities of large language models (LLMs) and vision-language models (VLMs). This approach leverages task-specific instructions, known as prompts, to enhance…
As large language models (LLMs) are deployed globally, creating pluralistic systems that can accommodate the diverse preferences and values of users worldwide becomes essential. We introduce EVALUESTEER, a benchmark to measure LLMs' and…
We propose a novel approach for decision making problems leveraging the generalization capabilities of large language models (LLMs). Traditional methods such as expert systems, planning algorithms, and reinforcement learning often exhibit…
Persona prompting can steer LLM generation towards a domain-specific tone and pattern. This behavior enables use cases in multi-agent systems where diverse interactions are crucial and human-centered tasks require high-level human…
Harnessing the reasoning power of Large Language Models (LLMs) for recommender systems is hindered by two fundamental challenges. First, current approaches lack a mechanism for automated, data-driven discovery of effective reasoning…
Large language models (LLMs) have multilingual capabilities and can solve tasks across various languages. However, we show that current LLMs make key decisions in a representation space closest to English, regardless of their input and…
Discrete Diffusion Language Models (DLMs) offer a promising non-autoregressive alternative for text generation, yet effective mechanisms for inference-time control remain relatively underexplored. Existing approaches include sampling-level…
The automated generation of hardware register-transfer level (RTL) code with large language models (LLMs) shows promise, yet current solutions struggle to produce syntactically and functionally correct code for complex digital designs. This…
Objective: This study investigates the potential of Large Language Models (LLMs) as an alternative to human expert elicitation for extracting structured causal knowledge and facilitating causal modeling in biometric and healthcare…
Purpose: Emotion is a fundamental component of human communication, shaping understanding, trust, and engagement across domains such as education, healthcare, and mental health. While large language models (LLMs) exhibit strong reasoning…
Large language models (LLMs) exhibit impressive capabilities in generation tasks but are prone to producing harmful, misleading, or biased content, posing significant ethical and safety concerns. To mitigate such risks, representation…