Kenji Kawaguchi | Web IR NLP Group @ NUShttps://www.comp.nus.edu.sg/~kanmy/wing/author/kenji-kawaguchi/Kenji KawaguchiHugo Blox Builder (https://hugoblox.com)en-usThu, 08 Aug 2024 00:00:00 +0000https://www.comp.nus.edu.sg/~kanmy/wing/author/kenji-kawaguchi/avatar_hu30e9d3fed2dc8bb85d7ace2bccb8ebe2_113960_270x270_fill_lanczos_center_3.pngKenji Kawaguchihttps://www.comp.nus.edu.sg/~kanmy/wing/author/kenji-kawaguchi/ComicVQA: A Benchmark for Visual Reasoning in Multimodal LLMshttps://www.comp.nus.edu.sg/~kanmy/wing/publication/gan-etal-2026-comicvqa/Wed, 01 Jul 2026 00:00:00 +0000https://www.comp.nus.edu.sg/~kanmy/wing/publication/gan-etal-2026-comicvqa/Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelineshttps://www.comp.nus.edu.sg/~kanmy/wing/publication/long-etal-2025-beyond/Fri, 01 Aug 2025 00:00:00 +0000https://www.comp.nus.edu.sg/~kanmy/wing/publication/long-etal-2025-beyond/What Makes a Good Natural Language Prompt?https://www.comp.nus.edu.sg/~kanmy/wing/publication/long-etal-2025-makes/Fri, 01 Aug 2025 00:00:00 +0000https://www.comp.nus.edu.sg/~kanmy/wing/publication/long-etal-2025-makes/LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMshttps://www.comp.nus.edu.sg/~kanmy/wing/publication/long-etal-2025-llms/Mon, 05 May 2025 00:00:00 +0000https://www.comp.nus.edu.sg/~kanmy/wing/publication/long-etal-2025-llms/Aligning Large Language Models with Human Opinions through Persona Selection and Value-Belief-Norm Reasoninghttps://www.comp.nus.edu.sg/~kanmy/wing/publication/dblp-confcoling-do-kkc-25/Wed, 01 Jan 2025 00:00:00 +0000https://www.comp.nus.edu.sg/~kanmy/wing/publication/dblp-confcoling-do-kkc-25/Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learninghttps://www.comp.nus.edu.sg/~kanmy/wing/publication/mcts-dpo-2024/Sat, 14 Dec 2024 00:00:00 +0000https://www.comp.nus.edu.sg/~kanmy/wing/publication/mcts-dpo-2024/Multi-expert Prompting Improves Reliability, Safety and Usefulness of Large Language Modelshttps://www.comp.nus.edu.sg/~kanmy/wing/publication/long-etal-2024-multi-expert/Thu, 12 Dec 2024 00:00:00 +0000https://www.comp.nus.edu.sg/~kanmy/wing/publication/long-etal-2024-multi-expert/Reasoning Robustness of LLMs to Adversarial Typographical Errorshttps://www.comp.nus.edu.sg/~kanmy/wing/publication/gan-etal-2024-reasoning/Tue, 12 Nov 2024 00:00:00 +0000https://www.comp.nus.edu.sg/~kanmy/wing/publication/gan-etal-2024-reasoning/Prompt Optimization via Adversarial In-Context Learninghttps://www.comp.nus.edu.sg/~kanmy/wing/publication/long-etal-2024-prompt/Thu, 08 Aug 2024 00:00:00 +0000https://www.comp.nus.edu.sg/~kanmy/wing/publication/long-etal-2024-prompt/Self-Evaluation Guided Beam Search for Reasoninghttps://www.comp.nus.edu.sg/~kanmy/wing/publication/selfeval-decoding-2023/Sun, 10 Dec 2023 00:00:00 +0000https://www.comp.nus.edu.sg/~kanmy/wing/publication/selfeval-decoding-2023/