activity
20242026
collaborators

6 papers

cs.CL2026

GRPO for Financial Advice Generation: Outperforming Commercial LLMs under CATE Evaluation

Ofir Ben Shoham, Shrutendra Harsola, Vignesh Subrahmaniam +3

Generating actionable financial advice from business records demands that models integrate numerical reasoning, domain knowledge, and sound judgment, while avoiding recommendations…

cs.CL2026

MedUPS: Towards Diagnostic Assistance in Uncommon Medical Cases with Large Language Models

Ofir Ben Shoham, Oriel Perets, Nir Grinberg +1

Uncommon and off-guideline cases are difficult for clinical decision support, because physicians must make a series of management decisions under diagnostic uncertainty and rarely…

cs.CL2026

Balancing Coverage and Draft Latency in Vocabulary Trimming for Faster Speculative Decoding

Ofir Ben Shoham

Speculative decoding accelerates inference for Large Language Models by using a lightweight draft model to propose candidate tokens that are verified in parallel by a larger target…

cs.CL2025

CUPCase: Clinically Uncommon Patient Cases and Diagnoses Dataset

Oriel Perets, Ofir Ben Shoham, Nir Grinberg +1

Medical benchmark datasets significantly contribute to developing Large Language Models (LLMs) for medical knowledge extraction, diagnosis, summarization, and other uses. Yet, curr…

cs.CL2024

MedConceptsQA: Open Source Medical Concepts QA Benchmark

Ofir Ben Shoham, Nadav Rappoport

We present MedConceptsQA, a dedicated open source benchmark for medical concepts question answering. The benchmark comprises of questions of various medical concepts across differe…

cs.CL2024

CPLLM: Clinical Prediction with Large Language Models

Ofir Ben Shoham, Nadav Rappoport

We present Clinical Prediction with Large Language Models (CPLLM), a method that involves fine-tuning a pre-trained Large Language Model (LLM) for clinical disease and readmission…