collaborators

8 papers

cs.CL2026

Post-training is (Massive) Supervised Learning

Michael Hassid, Yossi Adi, Roy Schwartz

The prevailing paradigm for training LLMs has evolved to rely on a massive post-training phase consisting of SFT and RL. In this position paper, we argue that this methodology effe…

cs.CL2026

Self-Execution Simulation Improves Coding Models

Gallil Maimon, Ori Yoran, Felix Kreuk +4

A promising research direction in enabling LLMs to generate consistently correct code involves addressing their inability to properly estimate program execution, particularly for c…

cs.CL2026

Linguistically Informed Evaluation of Multilingual ASR for African Languages

Fei-Yueh Chen, Lateef Adeleke, C. M. Downey

Word Error Rate (WER) mischaracterizes ASR models' performance for African languages by combining phonological, tone, and other linguistic errors into a single lexical error. By co…

cs.CL2026

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning

Michael Hassid, Gabriel Synnaeve, Yossi Adi +1

Reasoning large language models (LLMs) heavily rely on scaling test-time compute to perform complex reasoning tasks by generating extensive "thinking" chains. While demonstrating i…

cs.CL2025

More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG

Shahar Levy, Nir Mazor, Lihi Shalmon +2

Retrieval-Augmented Generation (RAG) enhances the accuracy of Large Language Model (LLM) responses by leveraging relevant external documents during generation. Although previous st…

cs.CL2025

On Pruning State-Space LLMs

Tamer Ghattas, Michael Hassid, Roy Schwartz

Recent work proposed state-space models (SSMs) as an efficient alternative to transformer-based LLMs. Can these models be pruned to further reduce their computation costs? We adapt…