activity
20172024
most citedImproving alignment of dialogue agents via targeted human judgements

133 citations · 462 across the 38 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2023

Baichuan 2: Open Large-scale Language Models

Aiyuan Yang, Bin Xiao, Bingning Wang +52

Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing…

cs.CL2023

Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering

Fangkai Yang, Pu Zhao, Zezhong Wang +6

Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average d…

cs.CL20221 cited

Revisiting Attention Weights as Explanations from an Information Theoretic Perspective

Bingyang Wen, K. P. Subbalakshmi, Fan Yang

Attention mechanisms have recently demonstrated impressive performance on a range of NLP tasks, and attention scores are often used as a proxy for model explainability. However, th…

cs.CL202113 cited

Density-Based Dynamic Curriculum Learning for Intent Detection

Yantao Gong, Cao Liu, Jiazhen Yuan +6

Pre-trained language models have achieved noticeable performance on the intent detection task. However, due to assigning an identical weight to each sample, they suffer from the ov…

cs.CL20201 cited

Pattern-aware Data Augmentation for Query Rewriting in Voice Assistant Systems

Yunmo Chen, Sixing Lu, Fan Yang +3

Query rewriting (QR) systems are widely used to reduce the friction caused by errors in a spoken language understanding pipeline. However, the underlying supervised models require…

cs.CL2020

Multi-Aspect Sentiment Analysis with Latent Sentiment-Aspect Attribution

Yifan Zhang, Fan Yang, Marjan Hosseinia +1

In this paper, we introduce a new framework called the sentiment-aspect attribution module (SAAM). SAAM works on top of traditional neural networks and is designed to address the p…