English
Related papers

Related papers: Monitoring Latent World States in Language Models …

200 papers

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

Computation and Language · Computer Science 2023-12-25 Afra Amini , Massimiliano Ciaramita

Our intention is to provide a definitive reference on what it would take to safely make use of generative/predictive models in the absence of a solution to the Eliciting Latent Knowledge problem. Furthermore, we believe that large language…

Artificial Intelligence · Computer Science 2023-02-07 Evan Hubinger , Adam Jermyn , Johannes Treutlein , Rubi Hudson , Kate Woolverton

Metacognition -- assessing the quality of one's own cognitive performance -- guides adaptive behavior across species. Substantial research demonstrates that confidence signals can be extracted from language model outputs, yet a fundamental…

Machine Learning · Computer Science 2026-05-20 Dharshan Kumaran , Nathaniel Daw , Simon Osindero , Petar Veličković , Viorica Patraucean

Language model prompt optimization research has shown that semantically and grammatically well-formed manually crafted prompts are routinely outperformed by automatically generated token sequences with no apparent meaning or syntactic…

Computation and Language · Computer Science 2023-10-25 Corentin Kervadec , Francesca Franzon , Marco Baroni

Since language models are used to model a wide variety of languages, it is natural to ask whether the neural architectures used for the task have inductive biases towards modeling particular types of languages. Investigation of these biases…

Computation and Language · Computer Science 2021-06-03 Jennifer C. White , Ryan Cotterell

Language models (LMs) are trained on collections of documents, written by individual human agents to achieve specific goals in an outside world. During training, LMs have access only to text of these documents, with no direct evidence of…

Computation and Language · Computer Science 2022-12-06 Jacob Andreas

We present a model of pragmatic referring expression interpretation in a grounded communication task (identifying colors from descriptions) that draws upon predictions from two recurrent neural network classifiers, a speaker and a listener,…

Computation and Language · Computer Science 2017-05-17 Will Monroe , Robert X. D. Hawkins , Noah D. Goodman , Christopher Potts

Advances in unsupervised probes such as Contrast-Consistent Search (CCS), which reveal latent beliefs without relying on token outputs, raise the question of whether these methods can reliably assess model alignment. We investigate this by…

Computation and Language · Computer Science 2025-12-01 Sabrina Sadiekh , Elena Ericheva , Chirag Agarwal

The success of neural networks on a diverse set of NLP tasks has led researchers to question how much these networks actually ``know'' about natural language. Probes are a natural way of assessing this. When probing, a researcher chooses a…

Computation and Language · Computer Science 2020-05-26 Tiago Pimentel , Josef Valvoda , Rowan Hall Maudslay , Ran Zmigrod , Adina Williams , Ryan Cotterell

Large language models are increasingly used as writing tools and pedagogical resources in English for Academic Purposes, but it remains unclear whether they encode culturally differentiated representations when generating academic text.…

Computation and Language · Computer Science 2026-04-15 Paul Jackson , Ruizhe Li , Elspeth Edelstein

Social norms are implicit, culturally grounded expectations that guide interpersonal communication. Unlike factual commonsense, norm reasoning is subjective, context-dependent, and varies across cultures, posing challenges for computational…

Computation and Language · Computer Science 2025-11-14 Pritish Sahu , Anirudh Som , Dimitra Vergyri , Ajay Divakaran

Recent advancements in controllable expressive speech synthesis, especially in text-to-speech (TTS) models, have allowed for the generation of speech with specific styles guided by textual descriptions, known as style prompts. While this…

Computation and Language · Computer Science 2025-02-11 Chun-Yi Kuan , Hung-yi Lee

We study the role of linguistic context in predicting quantifiers (`few', `all'). We collect crowdsourced data from human participants and test various models in a local (single-sentence) and a global context (multi-sentence) condition.…

Computation and Language · Computer Science 2018-06-04 Sandro Pezzelle , Shane Steinert-Threlkeld , Raffaela Bernardi , Jakub Szymanik

Retrieval-Augmented Generation (RAG) enhances language models by retrieving and incorporating relevant external knowledge. However, traditional retrieve-and-generate processes may not be optimized for real-world scenarios, where queries…

Computation and Language · Computer Science 2025-02-28 Ingeol Baek , Hwan Chang , Byeongjeong Kim , Jimin Lee , Hwanhee Lee

In this paper, we evaluate the capability of transformer-based language models in making inferences over uncertain text that includes uncertain rules of reasoning. We cover both Pre-trained Language Models (PLMs) and generative Large…

Computation and Language · Computer Science 2024-02-12 Aliakbar Nafar , Kristen Brent Venable , Parisa Kordjamshidi

Recently, pretrained language models (PLMs) have had exceptional success in language generation. To leverage the rich knowledge encoded by PLMs, a simple yet powerful paradigm is to use prompts in the form of either discrete tokens or…

Computation and Language · Computer Science 2022-10-04 Tianyi Tang , Junyi Li , Wayne Xin Zhao , Ji-Rong Wen

Prompting inputs with natural language task descriptions has emerged as a popular mechanism to elicit reasonably accurate outputs from large-scale generative language models with little to no in-context supervision. This also helps gain…

Computation and Language · Computer Science 2023-08-17 Lisa Bauer , Karthik Gopalakrishnan , Spandana Gella , Yang Liu , Mohit Bansal , Dilek Hakkani-Tur

Large language models have demonstrated surprising ability to perform in-context learning, i.e., these models can be directly applied to solve numerous downstream tasks by conditioning on a prompt constructed by a few input-output examples.…

Computation and Language · Computer Science 2023-04-03 Huan Ma , Changqing Zhang , Yatao Bian , Lemao Liu , Zhirui Zhang , Peilin Zhao , Shu Zhang , Huazhu Fu , Qinghua Hu , Bingzhe Wu

A growing body of literature has focused on detailing the linguistic knowledge embedded in large, pretrained language models. Existing work has shown that non-linguistic biases in models can drive model behavior away from linguistic…

Computation and Language · Computer Science 2021-06-03 Forrest Davis , Marten van Schijndel

Interpretability and explainability of AI are becoming increasingly important in light of the rapid development of large language models (LLMs). This paper investigates the interpretation of LLMs in the context of the knowledge-based…

Computation and Language · Computer Science 2024-06-05 Valeriya Goloviznina , Evgeny Kotelnikov