11 citations · 18 across the 5 of their papers we have counts for
6 papers
Beyond Experience: Knowledge-Guided Evolution for NPU Kernel Generation
Xi Chen, Ming Shen, Haotian Yan +2
LLM agents have become capable kernel engineers on mainstream GPU stacks, but they struggle on emerging accelerators such as Ascend NPUs, whose programming model is barely represen…
Rethinking Data Selection for Supervised Fine-Tuning
Ming Shen
Although supervised finetuning (SFT) has emerged as an essential technique to align large language models with humans, it is considered superficial, with style learning being its n…
Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization
Ming Shen, Jie Ma, Shuai Wang +4
Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews. However, generating aspect-specific and general summaries i…
Unsupervised Pronoun Resolution via Masked Noun-Phrase Prediction
Ming Shen, Pratyay Banerjee, Chitta Baral
In this work, we propose Masked Noun-Phrase Prediction (MNPP), a pre-training strategy to tackle pronoun resolution in a fully unsupervised setting. Firstly, We evaluate our pre-tr…
TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
Bill Yuchen Lin, Dong-Ho Lee, Ming Shen +4
Training neural models for named entity recognition (NER) in a new domain often requires additional human annotations (e.g., tens of thousands of labeled instances) that are usuall…
CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning
Bill Yuchen Lin, Wangchunshu Zhou, Ming Shen +4
Recently, large-scale pre-trained language models have demonstrated impressive performance on several commonsense-reasoning benchmark datasets. However, building machines with comm…