Related papers: Evaluating Steering Techniques using Human Similar…
System prompts provide a lightweight yet powerful mechanism for conditioning large language models (LLMs) at inference time. While prior work has focused on English-only settings, real-world deployments benefit from having a single prompt…
Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt…
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…
Despite growing interest in using Large Language Models (LLMs) for educational assessment, it remains unclear how closely they align with human scoring. We present a systematic evaluation of instruction-tuned LLMs across three open…
Large language models (LLMs) are increasingly being used as decision aids. However, users have diverse values and preferences that can affect their decision-making, which requires novel methods for LLM alignment and personalization.…
Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inference, has emerged…
A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…
Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…
Large Language Models (LLMs) have demonstrated their capabilities across various tasks, from language translation to complex reasoning. Understanding and predicting human behavior and biases are crucial for artificial intelligence (AI)…
Large language models (LLMs) have exploded in popularity in the past few years and have achieved undeniably impressive results on benchmarks as varied as question answering and text summarization. We provide a simple new prompting strategy…
The emergence of Large Language Models (LLMs) as chat assistants capable of generating human-like conversations has amplified the need for robust evaluation methods, particularly for open-ended tasks. Conventional metrics such as EM and F1,…
Performance of Large Language Models (LLMs) on multiple-choice tasks differs markedly between symbol-based and cloze-style evaluation formats. The observed discrepancies are systematically attributable to task characteristics: natural…
Large Language Model (LLM) deployment requires guiding the LLM to recognize and not answer unsafe prompts while complying with safe prompts. Previous methods for achieving this require adjusting model weights along with other expensive…
Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering} provides a lightweight alternative to prompt engineering…
Whether large language models (LLMs) process language similarly to humans has been the subject of much theoretical and practical debate. We examine this question through the lens of the production-interpretation distinction found in human…
Large Language Models (LLMs) have revolutionised the capability of AI models in comprehending and generating natural language text. They are increasingly being used to empower and deploy agents in real-world scenarios, which make decisions…
Recent advancements in Large Language Models (LLMs) have brought them closer to matching human cognition across a variety of tasks. How well do these models align with human performance in detecting and mapping analogies? Prior research has…
Ensuring that large language models (LLMs) reflect diverse user values and preferences is crucial as their user bases expand globally. It is therefore encouraging to see the growing interest in LLM personalization within the research…
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…
Large Language Models (LLMs) exhibit impressive reasoning abilities, yet their reliance on structured step-by-step processing reveals a critical limitation. In contrast, human cognition fluidly adapts between intuitive, heuristic (System 1)…