CV
The full cv can be found by clicking the icon on the right.
Table of contents
- General Information
- Education
- Professional Experience
- (Selected) Side Research Projects
- Honors and Awards
- Service
- Leadership Experience
General Information
Full Name | Bingsheng "Arthur" Yao |
Current Occupation | 5th Year Ph.D. Student in Computer Science |
One-sentence Introduction? | Hanc marginis exiguitās nōn caperet (Fermat, n.d.) |
Education
-
2024 Ph.D. in Computer Science
Rensselaer Polytechnic Institute - Thesis Topic
- Enhance Machine Reasoning with Human Rationales
- Thesis Topic
-
2019 MS in Information Technology & Web Science
Rensselaer Polytechnic Institute -
2018 BS in Computer & Systems Engineering
Rensselaer Polytechnic Institute
Professional Experience
-
2022 - 2023 Objective Human Explanation Evaluation
IBM AIRC Fellowship (Rensselaer Polytechnic Institute & IBM Research) - Proposed a prompt-based unified data format for different tasks
- Enhanced the established Simulatability score with a novel metric to evaluate explanations' helpfulness at fine-tuning and inference
- Our metric can evaluate 5 datasets with 2 models (T5 and BART) consistently, while the established metric falls short
-
2022 - 2023 Active Learning for Human Labels and Explanations
IBM AIRC Fellowship (Rensselaer Polytechnic Institute & IBM Research) - Proposed a dual-model AL framework to generate natural language explanations as additional information for the prediction model
- Designed a novel AL selection strategy based on the similarity between unlabeled data and human-annotated explanations
- Justified human explanations with our AL framework are beneficial for the prediction model to perform better and converge faster
-
2021 QA-Pair Generation (QAG) for Children Storybooks
Summer Research Extern (IBM Research) - Implemented a QAG system with 1). a heuristics-based answer extraction module, question; 2). a fine-tuned BART-based question generation module; 3). a DistilBERT-based ranking module to rank and select best QA-pairs
- Outperformed 2 SOTA QAG systems on the FairytaleQA dataset in terms of the mean average ROUGE-L precision at top 1, 3, 5, and 10 QA-pairs generated per story section
- Developed an interactive story-telling web application built upon our QAG system and justified its usefulness through a user study with 12 pairs of parents and children
-
2021 FairytaleQA Dataset for Children Education
Summer Research Extern (IBM Research) - Supervised education experts with carefully designed annotation schema to create 10, 580 QA-pairs on 278 fairytale stories
- Benchmarked FairytaleQA dataset can provide helpfulness on Question Answering and Question Generation tasks by fine-tuning various SOTA language models and performing in-depth analysis
(Selected) Side Research Projects
-
2023 Instruction-finetune LLM for Mental Issue Detection
- Curated high-quality human-annotated datasets for mental issue detection in online communities
- Designed prompts for augmented tasks with curated datasets and instruction-fine-tuned an Alpaca and FLAN-T5 model
- Benchmarked with SOTA models (e.g., fine-tuned Alpaca-Lora, mental-RoBERTa) and conducted extensive ablation studies on prompt selection, subsampling, and transfer learning
-
2023 QA Annotation Framework with Extern KG Support
- The framework supports human annotators to select a preferred concept, then retrieve and rank the most relevant Commonsense Knowledge from ConceptNet to facilitate QA-pair annotation
- Human evaluation justified that expert-created QA-pairs with our framework are preferred to the ones generated by carefully prompted GPT-3.5 few-shot approaches
Honors and Awards
-
2019 Member of Upsilon Pi Epsilon
- The International Honor Society for the Computing and Information Disciplines
-
2019 Member of Gamma Nu Eta
- The National Information Technology Honor Society
Service
-
2023 Reviewer
- ACL 2023 [2], EMNLP 2023 [5], ACL ARR Aug [1]
Leadership Experience
-
2018 Teaching Assistant
- Computer Organization
-
2019 Teaching Assistant
- Introduction of AI
-
2023 Teaching Assistant
- Computer Organization