연세대학교 첨단컴퓨팅학부, 세계 최고 권위 자연어처리 학회 'ACL 2026'에서 20개 논문 채택

우리 연세대학교 첨단컴퓨팅학부가 자연어처리(NLP) 및 인공지능 분야 세계 최고 권위 학회인 'ACL(Association for Computational Linguistics) 2026'에서 다수의 논문을 게재하며 글로벌 연구 역량을 다시 한번 입증했습니다.

이번 성과는 인공지능 및 소프트웨어 중심 연구를 선도하는 우리 학부 교수진의 끊임없는 노력이 결실을 맺은 것으로, 학부의 학문적 위상을 높이는 데 크게 기여하였습니다.

✍️ 논문 제목 및 저자

(Oral)

1. 1. EMCee: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context

- Hamin Koo, Jaehyung Kim

3. 
   
4. 2. Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs

- Beomsik Cho, Jaehyung Kim

(Main)

1. 1. A Linguistics-Aware LLM Watermarking via Syntactic Predictability

- Shinwoo Park, Hyejin Park, Hyeseon An and Yo-Sub Han

2. 
   
3. 2. COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs

- Dasol Choi, DongGeon Lee, Brigitta Jesica Kartono, Helena Berndt, Taeyoun Kwon, Joonwon Jang, Haon Park, Hwanjo Yu*, Minsuk Kahng*

3. 
   3. Diagnosing Spatial Consistency across Perspectives and Viewpoints in Large Vision-Language Models

- Yoonji Kim,Jieun Kim, Yujin Jeong, Sung-Bae Cho

4. 
   
5. 4. Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding

- Jaehyun Jeon, Min Soo Kim, Janghan Yoon, Sumin Shim, Yejin Choi, Hanbin Kim, Dae Hyun Kim*, Youngjae Yu*

1. 5. Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models

•      - Youngji Roh, Hyunjin Cho, Jaehyung Kim

5. 6. Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data

- Minseo Kwak, Jaehyung Kim

6. 
   
7. 7. Injecting Context via Situation Working Memory for Logical Reasoning with LLMs,

- Jieun Kim, Seoha Lim, YoungHae Choi, Sung-Bae Cho

7. 
   
8. 8. LLMs as Knowledge Graph Refiners: Mitigating Factual Inconsistencies in Generative Knowledge Extraction

- Donghyun Kim, Hyeongjun Yang, Seokju Hwang, Kyong-Ho Lee, and Chanhee Lee

8. 
   
9. 9. P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist

- Kwangwook Seo, Dongha Lee

9. 
   
10. 10. RV-HATE: Reinforced Multi-Module Voting for Implicit Hate Speech Detection

- Yejin Lee, Hyeseon An and Yo-Sub Han

(Findings)

1. 1. ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code Generation

- Soohan Lim, Joonghyuk Hahn, Hyunwoo Park, Sang-Ki Ko and Yo-Sub Han

2. 
   
3. 2. Data-Efficient Adaptation to Contextual Shifts in LLM-based Conversational Recommendation

- Hyeongjun Yang, Donghyun Kim, Seokju Hwang, Midan Shim, KyuHwan Yeom, KaeHyun Um, and Kyong-Ho Lee

3. 
   
4. 3. DUSK: Do Not Unlearn Shared Knowledge

- Wonje Jeung*, Sangyeon Yoon*, Hyesoo Hong*, Soeun Kim, Seungju Han, Youngjae Yu, and Albert No

4. 
   
5. 4. PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints

- Minjun Park, Donghyun Kim, Hyeonjong Ju, Seungwon Lim, Dongwook Choi, Taeyoon Kwon, Minju Kim, Jinyoung Yeo

5. 
   
6. 5. Revisiting the Uniform Information Density Hypothesis in LLM Reasoning Traces

- Minju Gwak, Guijin Son, Jaehyung Kim

6. 
   
7. 6. SpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent Interleaving

- Shengmin Piao, Sanghyun Park

7. 
   
8. 7. Which bird does not have wings: Negative-constrained KGQA with Schema-guided Semantic Matching and Self-directed Refinement

- Midan Shim, Seokju Hwang, KaeHyun Um, and Kyong-Ho Lee

8. 
   
9. 8. Why These Documents? Explainable Generative Retrieval with Hierarchical Category Paths

- Sangam Lee, Ryang Heo, SeongKu Kang, Susik Yoon, Jinyoung Yeo, Dongha Lee

Image Source: ACL Official Website (https://2026.aclweb.org)