Papers by Minjoon Choi
Modal-specific Pseudo Query Generation for Video Corpus Moment Retrieval (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have shown promising results in video corpus moment retrieval . however, they relied on the expensive query annotations for the VCMR . |
| Approach: | They propose a self-supervised learning framework to localize video corpus moment without annotations. |
| Outcome: | The proposed framework can localize the video corpus moment without any explicit annotation on TVR dataset. |
Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation (2026.acl-long)
Copied to clipboard
Katelyn X. Mei, Yi-Li Hsu, Minjoon Choi, Zongwan Cao, Chenjun Xu, Bingbing Wen, Su Lin Blodgett, Lucy Lu Wang
| Challenge: | a large-scale analysis of human evaluation protocols for long-form generation tasks is lacking in current practice . current protocols lack proper standardization and operationalization, which can limit validity of evaluation . |
| Approach: | They conduct a large-scale analysis of human evaluation protocols for long-form generation tasks in *CL conference papers from 2023–2025. |
| Outcome: | The proposed evaluation protocols lack standardization and operationalization, the authors show . they also find that the evaluation protocols are inadequate for specific domains and tasks . |
MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension (D19-58)
Copied to clipboard
| Challenge: | MRQA datasets have been used to benchmark progress in general-purpose language understanding. |
| Approach: | They propose to combine 18 question answering datasets into one shared task to evaluate their generalization capabilities. |
| Outcome: | The best system achieved an average F1 score of 72.5 on the 12 held-out datasets, 10.7 absolute points higher than baseline based on BERT. |
Fixed Input Parameterization for Efficient Prompting (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that attaching prompts to the input is effective at conditioning Language Models (LMs) however, prompts are always included in the input text during inference, thus incurring substantial computational and memory overhead. |
| Approach: | They propose to inject a fixed prompt into the parameters of an LM to be an efficient alternative to attaching fixed prompts to the input. |
| Outcome: | The proposed method can be up to 280 times more efficient in terms of FLOPs than previous approaches. |
Generative Prompt Internalization (2025.naacl-long)
Copied to clipboard
| Challenge: | Prompts used in large language model based applications are often fixed and lengthy, leading to significant computational overhead. |
| Approach: | They propose a method that internalizes complex prompts using a joint training approach and a data synthesis technique that auto-collects conversational datasets by swapping roles of agent and environment. |
| Outcome: | The proposed method internalizes complex prompts across agent-based applications and generates the content along with reasons for why it should change accordingly. |
Confidence-guided Refinement Reasoning for Zero-shot Question Answering (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing frameworks that generate single-step reasoning do not improve QA reasoning . |
| Approach: | They propose a framework that strategically constructs and refines sub-questions and their answers (sub-QAs) they argue that sub-QA does not always enhance QA reasoning . |
| Outcome: | The proposed framework can be integrated with existing QA models and benchmarks. |