Author

Jonathan Berant

h-index 5 View on Semantic Scholar

We have 3 of 22 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Dec 2025

Learning Steerable Clarification Policies with Collaborative Self-play

This work uses Reinforced Self-Training (ReST) to train the model to achieve high reward and shows this leads to a steerable policy that changes its behavior predictably conditioned on the provided costs, leading to higher reward and accuracy.

Jonathan Berant, M. Chen, Adam Fisch et al. · arXiv.org · 6 citations · ⚡2

#artificial intelligence Preprint Sep 2026

C$^{3}$T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees

C$^{3}$T (Counterfactual Causal Conversation Transformer), a thread-structured temporal model that jointly predicts node sentiment and shifts, learns sparse ancestor attribution, and supports counterfactual queries by forcing conversational intervention embeddings on or off to estimate potential outcomes, is proposed.

S M Rafiuddin, Atriya Sen, Thomas R. Davidson et al. · 0 citations

Jul 2026

CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion

This work proposes Collaborative Evaluation (CollabEval), a simple, effective, and principled method for exploiting dependencies between historical runs of different models on the same tasks to improve statistical efficiency.

Adam Fisch, Daniel Deutsch, Joshua Maynez et al. · arXiv.org · 2 citations