12 citations · 36 across the 32 of their papers we have counts for
7 papers · 1 filter
Domain Generalization Under Posterior Drift
Yilun Zhu, Naihao Deng, Naichen Shi +2
Domain generalization (DG) is the problem of generalizing from several distributions (or domains), for which labeled training data are available, to a new test domain for which no…
Benchmarking and Improving LLM Robustness for Personalized Generation
Chimaobi Okite, Naihao Deng, Kiran Bodipati +3
Recent years have witnessed a growing interest in personalizing the responses of large language models (LLMs). While existing evaluations primarily focus on whether a response alig…
CliniDial: A Naturally Occurring Multimodal Dialogue Dataset for Team Reflection in Action During Clinical Operation
Naihao Deng, Kapotaksha Das, Rada Mihalcea +2
In clinical operations, teamwork can be the crucial factor that determines the final outcome. Prior studies have shown that sufficient collaboration is the key factor that determin…
Are Human Interactions Replicable by Generative Agents? A Case Study on Pronoun Usage in Hierarchical Interactions
Naihao Deng, Rada Mihalcea
As Large Language Models (LLMs) advance in their capabilities, researchers have increasingly employed them for social simulation. In this paper, we investigate whether interactions…
Table as Thought: Exploring Structured Thoughts in LLM Reasoning
Zhenjie Sun, Naihao Deng, Haofei Yu +1
Large language models' reasoning abilities benefit from methods that organize their thought processes, such as chain-of-thought prompting, which employs a sequential structure to g…
What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects
Naihao Deng, Sheng Zhang, Henghui Zhu +7
Table modeling has progressed for decades. In this work, we revisit this trajectory and highlight emerging challenges in the LLM era, particularly the paradox of choice: the diffic…
Rethinking Table Instruction Tuning
Naihao Deng, Rada Mihalcea
Recent advances in table understanding have focused on instruction-tuning large language models (LLMs) for table-related tasks. However, existing research has overlooked the impact…