Related papers: A Language Model's Guide Through Latent Space

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

The linear subspace hypothesis (Bolukbasi et al., 2016) states that, in a language model's representation space, all information about a concept such as verbal number is encoded in a linear subspace. Prior work has relied on auxiliary…

In the era of digitalization, as individuals increasingly rely on digital platforms for communication and news consumption, various actors employ linguistic strategies to influence public perception. While models have become proficient at…

Numerous previous studies have sought to determine to what extent language models, pretrained on natural language text, can serve as useful models of human cognition. In this paper, we are interested in the opposite question: whether we can…

Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for learning features relevant to discriminative tasks.…

In the last decades, philosophers have begun using empirical data for conceptual analysis, but corpus-based conceptual analysis has so far failed to develop, in part because of the absence of reliable methods to automatically detect…

We introduce the identity labeling problem - given an individual in a social situation, can we predict what identity(ies) they will be labeled with by someone else? This problem remains a theoretical gap and methodological challenge,…

Humor is a natural and fundamental component of human interactions. When correctly applied, humor allows us to express thoughts and feelings conveniently and effectively, increasing interpersonal affection, likeability, and trust. However,…

The usual way to interpret language models (LMs) is to test their performance on different benchmarks and subsequently infer their internal processes. In this paper, we present an alternative approach, concentrating on the quality of LM…

Data-driven methods have achieved notable performance on intent detection, which is a task to comprehend user queries. Nonetheless, they are controversial for over-confident predictions. In some scenarios, users do not only care about the…

Large language models (LLMs) are now used in multi-turn workflows, but we still lack a clear way to measure when iteration helps and when it hurts. We present an evaluation framework for iterative refinement that spans ideation, code, and…

Recent work has demonstrated that the latent spaces of large language models (LLMs) contain directions predictive of the truth of sentences. Multiple methods recover such directions and build probes that are described as uncovering a…

When a language model generates text, the selection of individual tokens might lead it down very different reasoning paths, making uncertainty difficult to quantify. In this work, we consider whether reasoning language models represent the…

Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments. Despite their growing capability to perform multi-step reasoning and decision-making…

Large language models are increasingly being used in patient-facing medical question answering, where hallucinated outputs can vary widely in potential harm. However, existing hallucination standards and evaluation metrics focus primarily…

New intent discovery aims to uncover novel intent categories from user utterances to expand the set of supported intent classes. It is a critical task for the development and service expansion of a practical dialogue system. Despite its…

Recent language models have achieved impressive performance in natural language tasks by incorporating instructions with task input during fine-tuning. Since all samples in the same natural language task can be explained with the same task…

Text-to-image diffusion models have demonstrated the underlying risk of generating various unwanted content, such as sexual elements. To address this issue, the task of concept erasure has been introduced, aiming to erase any undesired…

Controlling stylistic attributes in large language models (LLMs) remains challenging, with existing approaches relying on either prompt engineering or post-training alignment. This paper investigates this challenge through the lens of…

Large Language Models (LLMs) are known to hallucinate, whereby they generate plausible but inaccurate text. This phenomenon poses significant risks in critical applications, such as medicine or law, necessitating robust hallucination…