Related papers: Steering Language Models Before They Speak: Logit-…
When prompting a language model (LM), users often expect the model to adhere to a set of behavioral principles across diverse tasks, such as producing insightful content while avoiding harmful or biased language. Instilling such principles…
Activation-based steering can personalize large language models at inference time, but its effects in educational settings remain unclear. We study persona vectors for seven character traits in short-answer generation and automated scoring…
Natural language processing (NLP) models trained on people-generated data can be unreliable because, without any constraints, they can learn from spurious correlations that are not relevant to the task. We hypothesize that enriching models…
Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of…
We introduce Contrastive Activation Addition (CAA), an innovative method for steering language models by modifying their activations during forward passes. CAA computes "steering vectors" by averaging the difference in residual stream…
In the constantly changing field of data-driven decision making, accurately predicting future events is crucial for strategic planning in various sectors. The emergence of Large Language Models (LLMs) marks a significant advancement in this…
Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data generated by a biased teacher model. Prior work has begun to characterize this phenomenon but leaves open…
Large Language Models (LLMs) have demonstrated remarkable capabilities in generating human-like text, but their output may not be aligned with the user or even produce harmful content. This paper presents a novel approach to detect and…
Recently, pre-trained language models mostly follow the pre-train-then-fine-tuning paradigm and have achieved great performance on various downstream tasks. However, since the pre-training stage is typically task-agnostic and the…
Large Language Models (LLMs) achieve remarkable performance through pretraining on extensive data. This enables efficient adaptation to diverse downstream tasks. However, the lack of interpretability in their underlying mechanisms limits…
Chain-of-Thought (CoT) prompting has improved the reasoning performance of large language models (LLMs), but it remains unclear why it works and whether it is the unique mechanism for triggering reasoning in large language models. In this…
With the emergence of large language models (LLMs) as a powerful class of generative artificial intelligence (AI), their use in tutoring has become increasingly prominent. Prior works on LLM-based tutoring typically learn a single tutor…
There is growing interest in AI systems that support human decision-making in high-stakes domains (e.g., medical diagnosis) to improve decision quality and reduce cognitive load. Mainstream approaches pair human experts with a…
Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been proposed to explain these methods, yet their common goal of…
Controlling the behavior of text-to-image generative models is critical for safe and practical deployment. Existing safety approaches typically rely on model fine-tuning or curated datasets, which can degrade generation quality or limit…
Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models. Controlled generation methods for DLMs, imported from autoregressive models, apply…
Thinking LLMs produce reasoning traces before answering. Prior activation steering work mainly targets on shaping these traces. It remains less understood how answer tokens actually read and integrate the reasoning to produce reliable…
Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…
Early identification of suicide risk is crucial for preventing suicidal behaviors. As a result, the identification and study of patterns and markers related to suicide risk have become a key focus of current research. In this paper, we…
Vision-Language Models (VLMs) excel at zero-shot inference but often degrade under test-time domain shifts. For this reason, episodic test-time adaptation strategies have recently emerged as powerful techniques for adapting VLMs to a single…