5 papers · 1 filter
How Quantization Shapes Bias in Large Language Models
Federico Marcuzzi, Xuefei Ning, Roy Schwartz +1
This work presents a comprehensive evaluation of how quantization affects model bias, with particular attention to its impact on individual demographic subgroups. We focus on weigh…
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…
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
Yufeng Du, Minyang Tian, Srikanth Ronanki +7
Large language models (LLMs) often fail to scale their performance on long-context tasks performance in line with the context lengths they support. This gap is commonly attributed…
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…
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…