Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Yuan, Peiwen"'
Autor:
Li, Yiwei, Shi, Jiayi, Feng, Shaoxiong, Yuan, Peiwen, Wang, Xinglin, Pan, Boyuan, Wang, Heda, Hu, Yao, Li, Kan
Instruction data is crucial for improving the capability of Large Language Models (LLMs) to align with human-level performance. Recent research LIMA demonstrates that alignment is essentially a process where the model adapts instructions' interaction
Externí odkaz:
http://arxiv.org/abs/2409.19680
Autor:
Yuan, Peiwen, Feng, Shaoxiong, Li, Yiwei, Wang, Xinglin, Zhang, Yueqi, Tan, Chuyi, Pan, Boyuan, Wang, Heda, Hu, Yao, Li, Kan
In-Context Learning (ICL) enables large language models (LLMs) to achieve rapid task adaptation by learning from demonstrations. With the increase in available context length of LLMs, recent experiments have shown that the performance of ICL does not
Externí odkaz:
http://arxiv.org/abs/2408.13987
Autor:
Yuan, Peiwen, Feng, Shaoxiong, Li, Yiwei, Wang, Xinglin, Pan, Boyuan, Wang, Heda, Hu, Yao, Li, Kan
The guidance from capability evaluations has greatly propelled the progress of both human society and Artificial Intelligence. However, as LLMs evolve, it becomes challenging to construct evaluation benchmarks for them with accurate labels on hard ta
Externí odkaz:
http://arxiv.org/abs/2408.13738
Autor:
Wang, Xinglin, Feng, Shaoxiong, Li, Yiwei, Yuan, Peiwen, Zhang, Yueqi, Pan, Boyuan, Wang, Heda, Hu, Yao, Li, Kan
Self-consistency (SC), a widely used decoding strategy for chain-of-thought reasoning, shows significant gains across various multi-step reasoning tasks but comes with a high cost due to multiple sampling with the preset size. Its variants, Adaptive
Externí odkaz:
http://arxiv.org/abs/2408.13457
Autor:
Wang, Xinglin, Yuan, Peiwen, Feng, Shaoxiong, Li, Yiwei, Pan, Boyuan, Wang, Heda, Hu, Yao, Li, Kan
Piaget's Theory of Cognitive Development (PTC) posits that the development of cognitive levels forms the foundation for human learning across various abilities. As Large Language Models (LLMs) have recently shown remarkable abilities across a wide va
Externí odkaz:
http://arxiv.org/abs/2408.09150
Autor:
Wang, Xinglin, Li, Yiwei, Feng, Shaoxiong, Yuan, Peiwen, Pan, Boyuan, Wang, Heda, Hu, Yao, Li, Kan
Self-consistency (SC), leveraging multiple samples from LLMs, shows significant gains on various reasoning tasks but struggles with free-form generation due to the difficulty of aggregating answers. Its variants, UCS and USC, rely on sample selection
Externí odkaz:
http://arxiv.org/abs/2407.02056
Autor:
Yuan, Peiwen, Wang, Xinglin, Feng, Shaoxiong, Pan, Boyuan, Li, Yiwei, Wang, Heda, Miao, Xupeng, Li, Kan
Publikováno v:
EACL 2024 main
Generative Retrieval (GR), autoregressively decoding relevant document identifiers given a query, has been shown to perform well under the setting of small-scale corpora. By memorizing the document corpus with model parameters, GR implicitly achieves
Externí odkaz:
http://arxiv.org/abs/2401.10487
Autor:
Li, Yiwei, Yuan, Peiwen, Feng, Shaoxiong, Pan, Boyuan, Wang, Xinglin, Sun, Bin, Wang, Heda, Li, Kan
Self-consistency (SC) has been a widely used decoding strategy for chain-of-thought reasoning. Despite bringing significant performance improvements across a variety of multi-step reasoning tasks, it is a high-cost method that requires multiple sampl
Externí odkaz:
http://arxiv.org/abs/2401.10480
Significant progress has been made in automatic text evaluation with the introduction of large language models (LLMs) as evaluators. However, current sample-wise evaluation paradigm suffers from the following issues: (1) Sensitive to prompt design; (
Externí odkaz:
http://arxiv.org/abs/2401.00437
Autor:
Li, Yiwei, Yuan, Peiwen, Feng, Shaoxiong, Pan, Boyuan, Sun, Bin, Wang, Xinglin, Wang, Heda, Li, Kan
Large Language Models (LLMs) have performed well on various reasoning tasks, but their inaccessibility and numerous parameters hinder wide application in practice. One promising way is distilling the reasoning ability from LLMs to small models by the
Externí odkaz:
http://arxiv.org/abs/2312.12832