Giwon Hong

28 papers A* 2B 1Journal 12Unranked 13
YearRankTypeTitle / Venue / Authors
2026 — conf
Analyzing LLM Instruction Optimization for Tabular Fact Verification.
EACL (Findings)
Xiaotang Du, Giwon Hong, Wai-Chung Kwan, Rohit Saxena, Ivan Titov, Pasquale Minervini, Emily Allaway
2026 J jnl
Analyzing LLM Instruction Optimization for Tabular Fact Verification.
CoRR
Xiaotang Du, Giwon Hong, Wai-Chung Kwan, Rohit Saxena, Ivan Titov, Pasquale Minervini, Emily Allaway
2026 J jnl
Compositional Steering of Large Language Models with Steering Tokens.
CoRR
Gorjan Radevski, Kiril Gashteovski, Giwon Hong, Carolin Lawrence, Goran Glavas
2025 — conf
Are We Done with MMLU?
NAACL (Long Papers)
Aryo Pradipta Gema, Joshua Ong Jun Leang, Giwon Hong, Alessio Devoto, Alberto Carlo Maria Mancino, Rohit Saxena, Xuanli He, Yu Zhao, Xiaotang Du, Mohammad Reza Ghasemi Madani, Claire Barale, Robert McHardy, Joshua Harris, Jean Kaddour, Emile van Krieken, Pasquale Minervini
2025 J jnl
GRADA: Graph-based Reranker against Adversarial Documents Attack.
CoRR
Jingjie Zheng, Aryo Pradipta Gema, Giwon Hong, Xuanli He, Pasquale Minervini, Youcheng Sun, Qiongkai Xu
2025 A* conf
GRADA: Graph-based Reranking against Adversarial Documents Attack.
EMNLP
Jingjie Zheng, Aryo Pradipta Gema, Giwon Hong, Xuanli He, Pasquale Minervini, Youcheng Sun, Qiongkai Xu
2025 — conf
Mixtures of In-Context Learners.
ACL (1)
Giwon Hong, Emile van Krieken, Edoardo Maria Ponti, Nikolay Malkin, Pasquale Minervini
2025 — conf
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering.
NAACL (Long Papers)
Yu Zhao, Alessio Devoto, Giwon Hong, Xiaotang Du, Aryo Pradipta Gema, Hongru Wang, Xuanli He, Kam-Fai Wong, Pasquale Minervini
2025 — conf
Theorem Prover as a Judge for Synthetic Data Generation.
ACL (1)
Joshua Ong Jun Leang, Giwon Hong, Wenda Li, Shay B. Cohen
2025 J jnl
Theorem Prover as a Judge for Synthetic Data Generation.
CoRR
Joshua Ong Jun Leang, Giwon Hong, Wenda Li, Shay B. Cohen
2024 J jnl
Analysing the Residual Stream of Language Models Under Knowledge Conflicts.
CoRR
Yu Zhao, Xiaotang Du, Giwon Hong, Aryo Pradipta Gema, Alessio Devoto, Hongru Wang, Xuanli He, Kam-Fai Wong, Pasquale Minervini
2024 J jnl
Are We Done with MMLU?
CoRR
Aryo Pradipta Gema, Joshua Ong Jun Leang, Giwon Hong, Alessio Devoto, Alberto Carlo Maria Mancino, Rohit Saxena, Xuanli He, Yu Zhao, Xiaotang Du, Mohammad Reza Ghasemi Madani, Claire Barale, Robert McHardy, Joshua Harris, Jean Kaddour, Emile van Krieken, Pasquale Minervini
2024 — conf
Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4.
SemEval@NAACL
Aryo Gema, Giwon Hong, Pasquale Minervini, Luke Daines, Beatrice Alex
2024 J jnl
Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4.
CoRR
Aryo Pradipta Gema, Giwon Hong, Pasquale Minervini, Luke Daines, Beatrice Alex
2024 J jnl
Mixtures of In-Context Learners.
CoRR
Giwon Hong, Emile van Krieken, Edoardo M. Ponti, Nikolay Malkin, Pasquale Minervini
2024 J jnl
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering.
CoRR
Yu Zhao, Alessio Devoto, Giwon Hong, Xiaotang Du, Aryo Pradipta Gema, Hongru Wang, Xuanli He, Kam-Fai Wong, Pasquale Minervini
2024 J jnl
The Hallucinations Leaderboard - An Open Effort to Measure Hallucinations in Large Language Models.
CoRR
Giwon Hong, Aryo Pradipta Gema, Rohit Saxena, Xiaotang Du, Ping Nie, Yu Zhao, Laura Perez-Beltrachini, Max Ryabinin, Xuanli He, Clémentine Fourrier, Pasquale Minervini
2024 — conf
Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise.
NAACL-HLT (Findings)
Giwon Hong, Jeonghwan Kim, Junmo Kang, Sung-Hyon Myaeng, Joyce Jiyoung Whang
2023 J jnl
Discern and Answer: Mitigating the Impact of Misinformation in Retrieval-Augmented Models with Discriminators.
CoRR
Giwon Hong, Jeonghwan Kim, Junmo Kang, Sung-Hyon Myaeng, Joyce Jiyoung Whang
2023 — conf
FinePrompt: Unveiling the Role of Finetuned Inductive Bias on Compositional Reasoning in GPT-4.
EMNLP (Findings)
Jeonghwan Kim, Giwon Hong, Sung-Hyon Myaeng, Joyce Jiyoung Whang
2022 — conf
Exploiting Numerical-Contextual Knowledge to Improve Numerical Reasoning in Question Answering.
NAACL-HLT (Findings)
Jeonghwan Kim, Junmo Kang, Kyung-Min Kim, Giwon Hong, Sung-Hyon Myaeng
2022 A* conf
Graph-Induced Transformers for Efficient Multi-Hop Question Answering.
EMNLP
Giwon Hong, Jeonghwan Kim, Junmo Kang, Sung-Hyon Myaeng
2021 — conf
Have You Seen That Number? Investigating Extrapolation in Question Answering Models.
EMNLP (1)
Jeonghwan Kim, Giwon Hong, Kyung-Min Kim, Junmo Kang, Sung-Hyon Myaeng
2021 J jnl
UHD-BERT: Bucketed Ultra-High Dimensional Sparse Representations for Full Ranking.
CoRR
Kyoungrok Jang, Junmo Kang, Giwon Hong, Sung-Hyon Myaeng, Joohee Park, Taewon Yoon, Hee-Cheol Seo
2021 — conf
Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval.
EMNLP (1)
Kyoungrok Jang, Junmo Kang, Giwon Hong, Sung-Hyon Myaeng, Joohee Park, Taewon Yoon, Hee-Cheol Seo
2020 B conf
Handling Anomalies of Synthetic Questions in Unsupervised Question Answering.
COLING
Giwon Hong, Junmo Kang, Doyeon Lim, Sung-Hyon Myaeng
2020 — conf
Regularization of Distinct Strategies for Unsupervised Question Generation.
EMNLP (Findings)
Junmo Kang, Giwon Hong, Haritz Puerto San Roman, Sung-Hyon Myaeng
2019 — conf
Aligning Open IE Relations and KB Relations using a Siamese Network Based on Word Embedding.
IWCS (1)
Rifki Afina Putri, Giwon Hong, Sung-Hyon Myaeng