activity
20182024
most citedMRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning

45 citations · 85 across the 21 of their papers we have counts for

collaborators
Showing cs.CLShow all

38 papers · 1 filter

cs.CL2024

Exploring the Learning Capabilities of Language Models using LEVERWORLDS

Eitan Wagner, Amir Feder, Omri Abend

Learning a model of a stochastic setting often involves learning both general structure rules and specific properties of the instance. This paper investigates the interplay between…

cs.CL2024

CONTESTS: a Framework for Consistency Testing of Span Probabilities in Language Models

Eitan Wagner, Yuli Slavutsky, Omri Abend

Although language model scores are often treated as probabilities, their reliability as probability estimators has mainly been studied through calibration, overlooking other aspect…

cs.CL2024

Identifying Narrative Patterns and Outliers in Holocaust Testimonies Using Topic Modeling

Maxim Ifergan, Renana Keydar, Omri Abend +1

The vast collection of Holocaust survivor testimonies presents invaluable historical insights but poses challenges for manual analysis. This paper leverages advanced Natural Langua…

cs.CL20231 cited

Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney

Shachar Don-Yehiya, Leshem Choshen, Omri Abend

Generating images with a Text-to-Image model often requires multiple trials, where human users iteratively update their prompt based on feedback, namely the output image. Taking in…

cs.CL20221 cited

Cognitive Simplification Operations Improve Text Simplification

Eytan Chamovitz, Omri Abend

Text Simplification (TS) is the task of converting a text into a form that is easier to read while maintaining the meaning of the original text. A sub-task of TS is Cognitive Simpl…

cs.CL20222 cited

DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering

Ella Neeman, Roee Aharoni, Or Honovich +3

Question answering models commonly have access to two sources of "knowledge" during inference time: (1) parametric knowledge - the factual knowledge encoded in the model weights, a…