Papers by Minjin Choi
From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have recently exhibited performance gains owing to a wide variety of prompting techniques, including Retrieval-Augmented Generation (RAG), Chain-of-Thought (CoT), and In-Context Learning (ICL). |
| Approach: | They propose a prompt compression method that captures the global context without compromising semantic consistency while detouring the necessity of pseudo-labels for training the compressor. |
| Outcome: | Empirical results show that the proposed method retains key contexts while reducing the prompt length by 80%. |
MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing studies have developed computational models to recognize metaphorical words in sentences. |
| Approach: | They propose a model that leverages contextualized word representation and linguistic metaphor identification theories to detect whether the target word is metaphorical. |
| Outcome: | The proposed model outperforms baseline models on four benchmark datasets . it leverages contextualized word representation and linguistic metaphor identification theories to detect whether the target word is metaphorical. |
GLEN: Generative Retrieval via Lexical Index Learning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for document retrieval bypass auxiliary index structures and can be optimized through end-to-end learning. |
| Approach: | They propose a method to generate a relevant document's identifier using an index learning strategy. |
| Outcome: | The proposed method achieves state-of-the-art or competitive performance on benchmark datasets. |
GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies rely on item metadata to construct abbreviated item IDs, leading to a loss of valuable details. |
| Approach: | They propose a Generative Recommender via semantic-aware multi-granular late fusion to integrate rich semantics efficiently with minimal information loss. |
| Outcome: | The proposed model outperforms eight state-of-the-art recommendation models on four benchmark datasets and achieves significant improvements of 11.5-16.0% in Recall@5 and 5.3-13.6% in NDCG@5. |
TRUEBench: Can LLM Response Meet Real-world Constraints as Productivity Assistant? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks fail to evaluate large language models' instruction-following capabilities . current benchmarks lack multilinguality, implicit constraints and multi-turn dialogue . |
| Approach: | a new benchmark is designed to evaluate large language models' instruction-following capabilities . the benchmark features input prompts across 12 languages and includes inter-instance multilingual instructions . |
| Outcome: | a new benchmark for large language models (LLMs) is designed to assess their performance in real-world settings. |