Search Results for author:
Found 7 papers, 7 papers with code
Efficient Dynamic Hard Negative Sampling for Dialogue Selection
Recent studies have demonstrated significant improvements in selection tasks, and a considerable portion of this success is attributed to incorporating informative negative samples during training.
Ranked #1 on
Conversational Response Selection
on E-commerce
Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning
Subsequently, we assess the performance on unseen tasks in a language different from the one used for training.
Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks
In this light, we introduce a simple yet effective task selection method that leverages instruction information alone to identify relevant tasks, optimizing instruction tuning for specific tasks.
External Knowledge Selection with Weighted Negative Sampling in Knowledge-grounded Task-oriented Dialogue Systems
In the experiment, we investigate the effect of weighted negative sampling, post-training, and style transfer.
TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models
Language Models (LMs) become outdated as the world changes; they often fail to perform tasks requiring recent factual information which was absent or different during training, a phenomenon called temporal misalignment.
Towards Continual Knowledge Learning of Language Models
By highlighting the critical causes of knowledge forgetting, we show that CKL is a challenging and important problem that helps us better understand and train ever-changing LMs.
Fine-grained Post-training for Improving Retrieval-based Dialogue Systems
During the multi-turn response selection, BERT focuses on training the relationship between the context with multiple utterances and the response.
Ranked #1 on
Conversational Response Selection
on RRS
