Papers by Minhyuk Kim
What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models (2026.findings-acl)
Copied to clipboard
Dasol Choi, Guijin Son, Hanwool Lee, Minhyuk Kim, Hyunwoo Ko, Teabin Lim, Eungyeol Ahn, Jungwhan Kim, Seunghyeok Hong, Youngsook Song
| Challenge: | HAERAE-Vision benchmarks feature clear, explicit prompts but are often informal and underspecified . state-of-the-art models achieve under 50% on original queries, compared to GPT-5 and Gemini 2.5 Pro . |
| Approach: | They propose a benchmark of 653 real-world visual questions from Korean online communities . they find that even state-of-the-art models achieve under 50% on original queries . |
| Outcome: | HAERAE-Vision benchmarks from Korean online communities yield 1,306 query variants . state-of-the-art models achieve under 50% on original queries, compared with smaller models . authors show that query explicitation alone yields 8 to 22 point improvements . |
Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have improved IE, but their potential for ATE has not been explored. |
| Approach: | They propose a retrieval-based prompting strategy that selects demonstrations according to syntactic rather than semantic similarity in a few-shot setting. |
| Outcome: | The proposed method improves performance on three specialized ATE benchmarks. |
Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models are often judged by their scores on standard benchmarks, yet such scores often overstate real capability since they mask the mix of skills a task actually demands. |
| Approach: | They propose a diagnostic framework that decomposes benchmark performance into ten cognitively grounded abilities and computes an Ability Impact Score (AIS) AIS quantifies how much each ability contributes to a model’s success on a given benchmark. |
| Outcome: | The proposed framework decomposes performance into ten cognitively grounded abilities and computes an Ability Impact Score (AIS) that quantifies how much each ability contributes to a model’s success on a given benchmark. |
Exploring Coding Spot: Understanding Parametric Contributions to LLM Coding Performance (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated proficiency in code generation and comprehension across multiple programming languages. |
| Approach: | They propose a parameter-localized subset of LLMs that facilitates coding capabilities. |
| Outcome: | The proposed model significantly improves performance on coding tasks while preserving non-coding functionalities. |
CLEAR: Cross-Lingual Enhancement in Retrieval via Reverse-training (2026.acl-long)
Copied to clipboard
| Challenge: | Existing multilingual embedding models often struggle to capture cross-lingual alignment during training. |
| Approach: | They propose a novel loss function that leverages an English passage as a bridge to strengthen alignments between target language and English. |
| Outcome: | The proposed model improves retrieval performance across cross-lingual scenarios while minimizing performance degradation in English. |
TORSO: Template-Oriented Reasoning Towards General Tasks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to generate responses using few-shot examples depend on the provided examples, limiting the model’s reasoning capabilities. |
| Approach: | They propose a model that emulates human reasoning during response generation by using curated few-shot prompts instead of manually crafted few-shot examples. |
| Outcome: | The proposed model achieves strong performance on diverse LLMs benchmarks with reasonable rationales. |