most citedEscape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning

3 citations · 5 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2024

Focused Large Language Models are Stable Many-Shot Learners

Peiwen Yuan, Shaoxiong Feng, Yiwei Li +7

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 LL…

cs.CL2024

Poor-Supervised Evaluation for SuperLLM via Mutual Consistency

Peiwen Yuan, Shaoxiong Feng, Yiwei Li +5

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 co…

cs.CL2024

Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation

Xinglin Wang, Yiwei Li, Shaoxiong Feng +5

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 ag…

cs.CL20243 cited

Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning

Yiwei Li, Peiwen Yuan, Shaoxiong Feng +5

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…

cs.CL20231 cited

BatchEval: Towards Human-like Text Evaluation

Peiwen Yuan, Shaoxiong Feng, Yiwei Li +4

Significant progress has been made in automatic text evaluation with the introduction of large language models (LLMs) as evaluators. However, current sample-wise evaluation paradig…