collaborators

7 papers

cs.CL2025

Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies

Nadav Timor, Jonathan Mamou, Daniel Korat +5

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generat…

cs.DC2025

Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference

Nadav Timor, Jonathan Mamou, Daniel Korat +6

This paper introduces distributed speculative inference (DSI), a novel inference algorithm that is provably faster than speculative inference (SI) [leviathan2023, chen2023, miao202…

cs.CL2025

HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly

Howard Yen, Tianyu Gao, Minmin Hou +5

Many benchmarks exist for evaluating long-context language models (LCLMs), yet developers often rely on synthetic tasks such as needle-in-a-haystack (NIAH) or an arbitrary subset o…

cs.CL2025

SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models

Daniel Fleischer, Moshe Berchansky, Gad Markovits +1

In the rapidly evolving field of Natural Language Processing, Large Language Models (LLMs) are tasked with increasingly complex reasoning challenges. Traditional methods like chain…

cs.CL2024

CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity

Moshe Berchansky, Daniel Fleischer, Moshe Wasserblat +1

State-of-the-art performance in QA tasks is currently achieved by systems employing Large Language Models (LLMs), however these models tend to hallucinate information in their resp…

cs.CL2024

Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models

Jonathan Mamou, Oren Pereg, Daniel Korat +4

Speculative decoding is commonly used for reducing the inference latency of large language models. Its effectiveness depends highly on the speculation lookahead (SL)-the number of…