most citedComparable Demonstrations are Important in In-Context Learning: A Novel Perspective on Demonstration Selection

1 citations · 1 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL2024

Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models

Haoran Liao, Jidong Tian, Shaohua Hu +2

Large language models (LLMs) still grapple with complex tasks like mathematical reasoning. Despite significant efforts invested in improving prefix prompts or reasoning process, th…

cs.CL20241 cited

Comparable Demonstrations are Important in In-Context Learning: A Novel Perspective on Demonstration Selection

Caoyun Fan, Jidong Tian, Yitian Li +2

In-Context Learning (ICL) is an important paradigm for adapting Large Language Models (LLMs) to downstream tasks through a few demonstrations. Despite the great success of ICL, the…

cs.CL2023

Chain-of-Thought Tuning: Masked Language Models can also Think Step By Step in Natural Language Understanding

Caoyun Fan, Jidong Tian, Yitian Li +3

Chain-of-Thought (CoT) is a technique that guides Large Language Models (LLMs) to decompose complex tasks into multi-step reasoning through intermediate steps in natural language f…

cs.CL2023

Accurate Use of Label Dependency in Multi-Label Text Classification Through the Lens of Causality

Caoyun Fan, Wenqing Chen, Jidong Tian +3

Multi-Label Text Classification (MLTC) aims to assign the most relevant labels to each given text. Existing methods demonstrate that label dependency can help to improve the model'…

cs.CV2023

MaxGNR: A Dynamic Weight Strategy via Maximizing Gradient-to-Noise Ratio for Multi-Task Learning

Caoyun Fan, Wenqing Chen, Jidong Tian +3

When modeling related tasks in computer vision, Multi-Task Learning (MTL) can outperform Single-Task Learning (STL) due to its ability to capture intrinsic relatedness among tasks.…

cs.CL2023

Improving the Out-Of-Distribution Generalization Capability of Language Models: Counterfactually-Augmented Data is not Enough

Caoyun Fan, Wenqing Chen, Jidong Tian +3

Counterfactually-Augmented Data (CAD) has the potential to improve language models' Out-Of-Distribution (OOD) generalization capability, as CAD induces language models to exploit c…