English
Related papers

Related papers: Characterizing Model-Native Skills

200 papers

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarchical syntactic features - as opposed to incorrect linear…

Computation and Language · Computer Science 2023-06-01 Aaron Mueller , Tal Linzen

A major driver of AI products today is the fact that new skills emerge in language models when their parameter set and training corpora are scaled up. This phenomenon is poorly understood, and a mechanistic explanation via mathematical…

Machine Learning · Computer Science 2023-11-07 Sanjeev Arora , Anirudh Goyal

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Computation and Language · Computer Science 2024-10-31 Rishabh Adiga , Besmira Nushi , Varun Chandrasekaran

Effective personalized feedback is critical to students' literacy development. Though LLM-powered tools now promise to automate such feedback at scale, LLMs are not language-neutral: they privilege standard academic English and reproduce…

Computation and Language · Computer Science 2026-03-16 Mei Tan , Lena Phalen , Dorottya Demszky

Value trade-offs are an integral part of human decision-making and language use, however, current tools for interpreting such dynamic and multi-faceted notions of values in language models are limited. In cognitive science, so-called…

Computation and Language · Computer Science 2026-03-03 Sonia K. Murthy , Rosie Zhao , Jennifer Hu , Sham Kakade , Markus Wulfmeier , Peng Qian , Tomer Ullman

Linearly transforming stimulus representations of deep neural networks yields high-performing models of behavioral and neural responses to complex stimuli. But does the test accuracy of such predictions identify genuine representational…

Neurons and Cognition · Quantitative Biology 2026-01-05 Itamar Avitan , Tal Golan

Model-agnostic feature attributions can provide local insights in complex ML models. If the explanation is correct, a domain expert can validate and trust the model's decision. However, if it contradicts the expert's knowledge, related work…

Machine Learning · Computer Science 2023-06-30 Joran Michiels , Maarten De Vos , Johan Suykens

Humans acquire knowledge by observing the external world, but also by introspection. Introspection gives a person privileged access to their current state of mind (e.g., thoughts and feelings) that is not accessible to external observers.…

Computation and Language · Computer Science 2024-10-18 Felix J Binder , James Chua , Tomek Korbak , Henry Sleight , John Hughes , Robert Long , Ethan Perez , Miles Turpin , Owain Evans

Although natural language is the default medium for Large Language Models (LLMs), its limited expressive capacity creates a profound bottleneck for complex problem-solving. While recent advancements in AI have relied heavily on scaling,…

Artificial Intelligence · Computer Science 2026-05-13 Zhiqin Yang , Yuhan Liu , Jingwen Fu , Pei Fu , Bo Han , Masashi Sugiyama , Nanning Zheng

The self-rationalising capabilities of large language models (LLMs) have been explored in restricted settings, using task/specific data sets. However, current LLMs do not (only) rely on specifically annotated data; nonetheless, they…

Computation and Language · Computer Science 2024-12-18 Jenny Kunz , Marco Kuhlmann

We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose an initial segmentation of the trajectories. Following that, a hierarchical variational inference…

We formalise the essential data of objective functions as equality constraints on composites of learners. We call these constraints "tasks", and we investigate the idealised view that such tasks determine model behaviours. We develop a…

Machine Learning · Computer Science 2025-05-06 Benjamin Rodatz , Ian Fan , Tuomas Laakkonen , Neil John Ortega , Thomas Hoffmann , Vincent Wang-Mascianica

Natural language processing (NLP) models often replicate or amplify social bias from training data, raising concerns about fairness. At the same time, their black-box nature makes it difficult for users to recognize biased predictions and…

Computation and Language · Computer Science 2026-02-12 Yifan Wang , Mayank Jobanputra , Ji-Ung Lee , Soyoung Oh , Isabel Valera , Vera Demberg

One of the most surprising and exciting discoveries in supervised learning was the benefit of overparameterization (i.e. training a very large model) to improving the optimization landscape of a problem, with minimal effect on statistical…

Machine Learning · Statistics 2020-07-17 Rares-Darius Buhai , Yoni Halpern , Yoon Kim , Andrej Risteski , David Sontag

Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether these self-explanations faithfully reflect the models'…

Computation and Language · Computer Science 2025-12-09 Tomoki Doi , Masaru Isonuma , Hitomi Yanaka

Understanding how language model performance varies with scale is critical to benchmark and algorithm development. Scaling laws are one approach to building this understanding, but the requirement of training models across many different…

Machine Learning · Computer Science 2024-10-03 Yangjun Ruan , Chris J. Maddison , Tatsunori Hashimoto

STEM education researchers are often interested in identifying moments of students' mechanistic reasoning for deeper analysis, but have limited capacity to search through many team conversation transcripts to find segments with a high…

Physics Education · Physics 2026-04-24 Kaitlin Gili , Mainak Nistala , Kristen Wendell , Michael C. Hughes

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically alignment requires fine-tuning a model, which is…

Computation and Language · Computer Science 2025-07-22 Anirudh Sundar , Sinead Williamson , Katherine Metcalf , Barry-John Theobald , Skyler Seto , Masha Fedzechkina

Alignment has quickly become a default ingredient in LLM development, with techniques such as reinforcement learning from human feedback making models act safely, follow instructions, and perform ever-better on complex tasks. While these…

Computation and Language · Computer Science 2025-09-16 Peter West , Christopher Potts
‹ Prev 1 3 4 5 6 7 10 Next ›