activity
20232026
most citedBenchmarking Large Language Models on Controllable Generation under Diversified Instructions

2 citations · 4 across the 13 of their papers we have counts for

collaborators
Showing 2023Show all

5 papers · 1 filter

cs.CL2023

E-CORE: Emotion Correlation Enhanced Empathetic Dialogue Generation

Fengyi Fu, Lei Zhang, Quan Wang +1

Achieving empathy is a crucial step toward humanized dialogue systems. Current approaches for empathetic dialogue generation mainly perceive an emotional label to generate an empat…

cs.CL2023

Grammatical Error Correction via Mixed-Grained Weighted Training

Jiahao Li, Quan Wang, Chiwei Zhu +2

The task of Grammatical Error Correction (GEC) aims to automatically correct grammatical errors in natural texts. Almost all previous works treat annotated training data equally, b…

cs.CL2023★ 1 cited

On the Calibration of Large Language Models and Alignment

Chiwei Zhu, Benfeng Xu, Quan Wang +2

As large language models attract increasing attention and find widespread application, concurrent challenges of reliability also arise at the same time. Confidence calibration, an…

cs.CL2023

Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation

Tianqi Zhong, Quan Wang, Jingxuan Han +2

Controllable text generation (CTG) aims to generate text with desired attributes, and decoding-time-based methods have shown promising performance on this task. However, in this pa…

cs.AI2023

Random Entity Quantization for Parameter-Efficient Compositional Knowledge Graph Representation

Jiaang Li, Quan Wang, Yi Liu +2

Representation Learning on Knowledge Graphs (KGs) is essential for downstream tasks. The dominant approach, KG Embedding (KGE), represents entities with independent vectors and fac…