Papers by Makoto Onizuka
Language-agnostic Representation from Multilingual Sentence Encoders for Cross-lingual Similarity Estimation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to extract language-specific information from multilingual sentence embeddings are remarkably successful in cross-lingual and multilingual NLU tasks. |
| Approach: | They propose to extract language-specific information from the original embedding and use it to retrieve an embeddable that fully represents the sentence’s meaning. |
| Outcome: | The proposed method outperforms baselines on cross-lingual sentences even in low-resource language pairs where only tens of thousands of parallel sentence pairs are available. |
Legal Fact Prediction: The Missing Piece in Legal Judgment Prediction (2025.emnlp-main)
Copied to clipboard
Junkai Liu, Yujie Tong, Hui Huang, Bowen Zheng, Yiran Hu, Peicheng Wu, Chuan Xiao, Makoto Onizuka, Muyun Yang, Shuyuan Zheng
| Challenge: | Existing studies use legal facts to predict judgments, but legal facts are difficult to obtain in early stages of litigation. |
| Approach: | They propose a legal fact prediction task that takes evidence from trial as input to make predictions in the absence of ground-truth legal facts. |
| Outcome: | The proposed task can predict court rulings without ground-truth legal facts . the first benchmark dataset, LFPBench, is used to evaluate the task . |
Edit Distance Based Curriculum Learning for Paraphrase Generation (2021.acl-srw)
Copied to clipboard
| Challenge: | Existing studies show that curriculum learning improves translation quality on machine translation . paraphrase generation allows a certain level of semantic divergence between source and target . |
| Approach: | They propose to apply curriculum learning to paraphrase generation for the first time . they propose to use edit distance to improve paraphrase quality . |
| Outcome: | The proposed method improves paraphrase generation quality, compared with previous methods . it uses edit distance, which is not possible for previous methods, the authors say . |
Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities in processing long contexts. |
| Approach: | They propose a training-free method that adaptively chooses the selection layer for KV cache reduction . they exploit the variance of token ranks ordered by attention score to optimize decoding . |
| Outcome: | The proposed method outperforms state-of-the-art token pruning methods on InfiniteBench, RULER, and NIAH benchmarks. |
Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents (2024.findings-emnlp)
Copied to clipboard
Zengqing Wu, Run Peng, Shuyuan Zheng, Qianying Liu, Xu Han, Brian Kwon, Makoto Onizuka, Shaojie Tang, Chuan Xiao
| Challenge: | Large Language Models (LLMs) are increasingly used in social simulations, where they are guided by carefully crafted instructions to exhibit human-like behaviors. |
| Approach: | They propose to use Large Language Models (LLMs) as agents to simulate the gradual transition from non-cooperative to cooperative behaviors of agents. |
| Outcome: | The proposed model can simulate the gradual transition from non-cooperative to cooperative behaviors in three competitive scenarios. |
Holistic Prediction on a Time-Evolving Attributed Graph (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for predicting future links, nodes, and attributes of time-evolving attributed graphs are not accurate. |
| Approach: | They propose a framework that predicts node attributes and topology changes such as appearance and disappearance of links and the emergence and loss of nodes. |
| Outcome: | The proposed framework improves on existing methods that assume that each link, node, and attribute prediction is independent and fails to predict new nodes that were not observed in the past. |