3 papers
cs.AI2025
Think Clearly: Improving Reasoning via Redundant Token Pruning
Daewon Choi, Jimin Lee, Jihoon Tack +7
Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe…
cs.CL2025
Mamba Drafters for Speculative Decoding
Daewon Choi, Seunghyuk Oh, Saket Dingliwal +9
Speculative decoding has emerged as a promising approach to accelerating large language model (LLM) generation using a fast drafter while maintaining alignment with the target mode…
cs.CL2024
Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization
Lei Xu, Mohammed Asad Karim, Saket Dingliwal +1
Large language models (LLMs) can generate fluent summaries across domains using prompting techniques, reducing the need to train models for summarization applications. However, cra…