From the 1 of 3 linked papers with an AI index.
4 papers · 1 filter
A Thorough Examination of Decoding Methods in the Era of LLMs
Chufan Shi, Haoran Yang, Deng Cai +4
Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focu…
Chain-of-Dictionary Prompting Elicits Translation in Large Language Models
Hongyuan Lu, Haoran Yang, Haoyang Huang +3
Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation (MNMT) even when trained without parallel data. Yet, despite the fa…
Unveiling the Generalization Power of Fine-Tuned Large Language Models
Haoran Yang, Yumeng Zhang, Jiaqi Xu +3
While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yiel…
A Frustratingly Simple Decoding Method for Neural Text Generation
Haoran Yang, Deng Cai, Huayang Li +3
We introduce a frustratingly simple, super efficient and surprisingly effective decoding method, which we call Frustratingly Simple Decoding (FSD), for neural text generation. The…