I’m looking for research/applied scientist internship for summer/fall 2024. Don’t hesitate to contact me if there is a match!
Research Focus
I am broadly interested in reasoning, which (IMHO) is a key aspect of human intelligence that sets us apart from other species. In the realm of reasoning, I’ve worked on:
- Building general-purpose verifier through rationale extraction from unlabelled data to provide process supervision during reasoning
- Logical reasoning that uses theorem prover Lean to help with the reasoning process [2]
- Decompositional entailment that formulates a consistent and theoretically grounded approach to annotating decompositional entailment dataset [3]
I’m also interested in the self-improvement capability of LLMs. If we begin with the “end” (superintelligence/AGI) in mind, relying on human input won’t get us there. We need to teach models to interact with the environment and self-improve. Specifically, I’ve worked on:
- Understanding the reason that prevents LLM from effective self-improvement [1]
- Building an environment that provides faithful feedback for self-improvement
- Incorporating reasoning techniques to solve issues during self-improvement
The role of training data and alignment in reasoning and self-improvement has always fascinated me. I would like to explore this further when I have more time and resources.
Selected Publications
SELF-[IN]CORRECT: LLMs Struggle with Refining Self-Generated Responses
Dongwei Jiang, Jingyu Zhang, Orion Weller, Nathaniel Weir, Benjamin Van Durme, Daniel Khashabi. arxiv preprint, 2024.LeanReasoner: Boosting Complex Logical Reasoning with Lean
Dongwei Jiang, Marcio Fonseca, Shay B. Cohen. NAACL Main Conference, 2024.Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic
Nathaniel Weir, Kate Sanders, Orion Weller, Shreya Sharma, Dongwei Jiang, Zhengping Jiang, Bhavana Dalvi Mishra, Oyvind Tafjord, Peter Jansen, Peter Clark, Benjamin Van Durme. arxiv preprint, 2024.
(for a full publication, please visit my Google Scholar)
More About Me
With six years of industry and research experience in speech processing and self-supervised models, my focus is shifting to LLM. To that end, I’m currently studying at JHU as a master’s student, working with Professor Daniel Khashabi and Benjamin Van Drume. I’ve also worked with Professor Shay Cohen from Edinburgh and Greg Durrett from UTA.
Reflecting on my career, I’ve observed a pattern where significant external events have impacted my role. While I was getting comfortable with my role at DiDi, the company encountered serious regulatory issues with the Chinese government, resulting in its delisting from New York Stock Exchange. During my time at YuanFuDao, the Double Reduction Policy was introduced, which imposed strict restrictions on YuanFuDao’s core business operations. As I was adapting to my position at Shopee, the company’s stock price dropped 80% due to the global economic crisis and the tensions between China and the US, leading to its extensive layoffs.
In my free time, I sometimes play Civ 6 or Hearthstone. I also run and go bouldering every other day - well, more like every three or four days, but who’s counting?