Related papers: Steering Language Models in Multi-Token Generation…
Understanding how latent representations evolve during generation is a central open problem in large language model interpretability. We introduce \textbf{Dynamical Manifold Evolution Theory} (DMET), a phenomenological framework that models…
Turn-taking is a fundamental mechanism in human communication that ensures smooth and coherent verbal interactions. Recent advances in Large Language Models (LLMs) have motivated their use in improving the turn-taking capabilities of Spoken…
Multilingual Large Language Models (LLMs) often exhibit hallucinations such as unintended code-switching, reducing reliability in downstream tasks. We propose latent-space language steering, a lightweight inference-time method that…
Where should we intervene in a language model (LM) to localize and control behaviors that are diffused across many tokens of a long-form response? We introduce Generative Causal Mediation (GCM), a procedure for selecting model components…
Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works-- specifically, what internal mechanisms steering vectors affect…
Multi-aspect controllable text generation is a more challenging and practical task than single-aspect control. Existing methods achieve complex multi-aspect control by fusing multiple controllers learned from single-aspect, but suffer from…
Recent advances in mechanistic interpretability have revealed that large language models (LLMs) develop internal representations corresponding not only to concrete entities but also distinct, human-understandable abstract concepts and…
Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased…
In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual information. Analogous to human episodic memory, where the retrieval of specific events is enabled by…
Even after fine-tuning and reinforcement learning, large language models (LLMs) can be difficult, if not impossible, to control reliably with prompts alone. We propose a new inference-time approach to enforcing syntactic and semantic…
While a lot of recent research focuses on enhancing the textual reasoning capabilities of Large Language Models (LLMs) by optimizing the multi-agent framework or reasoning chains, several benchmark tasks can be solved with 100\% success…
Large Language Models (LLMs) are now capable of generating highly fluent, human-like text. They enable many applications, but also raise concerns such as large scale spam, phishing, or academic misuse. While much work has focused on…
Deploying LLMs in real-world applications requires controllable output that satisfies multiple desiderata at the same time. While existing work extensively addresses LLM steering for a single behavior, \textit{compositional steering} --…
This paper investigates how large language models (LLMs) behave when faced with discrepancies between their parametric knowledge and conflicting information contained in a prompt. Building on prior question-answering (QA) research, we…
Reference-based Text-to-Speech (TTS) models can generate multiple, prosodically-different renditions of the same target text. Such models jointly learn a latent acoustic space during training, which can be sampled from during inference.…
Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…
Large language models benefit from training with a large amount of unlabeled text, which gives them increasingly fluent and diverse generation capabilities. However, using these models for text generation that takes into account target…
People are increasingly using technologies equipped with large language models (LLM) to write texts for formal communication, which raises two important questions at the intersection of technology and society: Who do LLMs write like (model…
Large language models have simplified the production of personalized translations reflecting predefined stylistic constraints. However, these systems still struggle when stylistic requirements are implicitly represented by a set of…
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…