大学 × Natural Language Processing
東京大学
Natural Language Processing / 2022–2026 LIVE
掲載論文 108 本
論文一覧
108 本
このEditionのランキングに掲載している論文です。同じ大学の複数著者による共著は1本にまとめています。
ランキングの対象論文 108 本と一致しています。
2026年
- A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models
掲載ID:
acl-anthology:2026.acl-long.552 - An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal
掲載ID:
acl-anthology:2026.acl-long.1694 - C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences
掲載ID:
acl-anthology:2026.acl-long.523 - CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models
掲載ID:
acl-anthology:2026.acl-long.2132 - Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety
掲載ID:
acl-anthology:2026.acl-long.2010 - Dual Alignment Between Language Model Layers and Human Sentence Processing
掲載ID:
acl-anthology:2026.acl-long.2143 - Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks
掲載ID:
acl-anthology:2026.acl-long.1846 - FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning
掲載ID:
acl-anthology:2026.acl-long.662 - Fine-Grained Analysis of Shared Syntactic Mechanisms in Language Models
掲載ID:
acl-anthology:2026.acl-long.2078 - How to Improve LLMs’ Performance on Specific Languages: A Perspective on LLM-Derived Language Similarity
掲載ID:
acl-anthology:2026.acl-long.691 - LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models
掲載ID:
acl-anthology:2026.acl-long.972 - Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge
掲載ID:
acl-anthology:2026.acl-long.1495 - Language Acquisition Device in Large Language Models
掲載ID:
acl-anthology:2026.acl-long.895 - MED-COREASONER: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning
掲載ID:
acl-anthology:2026.acl-long.1140 - Mapping the Circumplex of Affect: Geometric Analysis of Emotion Representations via Hyperspherical Contrastive Learning
掲載ID:
acl-anthology:2026.acl-long.772 - MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences
掲載ID:
acl-anthology:2026.acl-long.850 - NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning
掲載ID:
acl-anthology:2026.acl-long.345 - Quantifying and Mitigating Socially Desirable Responding in LLMs: A Desirability-Matched Graded Forced-Choice Psychometric Study
掲載ID:
acl-anthology:2026.acl-long.1865 - See2Refine: Vision-Language Feedback Improves LLM-Based eHMI Action Designers
掲載ID:
acl-anthology:2026.acl-long.1044 - Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentation
掲載ID:
acl-anthology:2026.acl-long.1626 - The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents
掲載ID:
acl-anthology:2026.acl-long.520 - The Imperfective Paradox in Large Language Models
掲載ID:
acl-anthology:2026.acl-long.689 - Understanding Emergent Misalignment via Feature Superposition Geometry
掲載ID:
acl-anthology:2026.acl-long.1402 - Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning
掲載ID:
acl-anthology:2026.acl-long.620 - Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings
掲載ID:
acl-anthology:2026.acl-long.2183 - (How) Do MLLMs Report Bistable Images Like Humans?
掲載ID:
acl-anthology:2026.emnlp-main.1744 - A Comparative Analysis of LLM Memorization at Statistical and Internal Levels: Cross-Model Commonalities and Model-Specific Signatures
掲載ID:
acl-anthology:2026.emnlp-main.1863 - Can MLLMs Read the Room? A Multimodal Benchmark for Assessing Deception in Multi-Party Social Interactions
掲載ID:
acl-anthology:2026.emnlp-main.905 - Cross-Centaur: Modeling Individual Decision-Making Across Psychological Tasks with Language Models
掲載ID:
acl-anthology:2026.emnlp-main.2235 - Cross-Lingual Representation Alignment by Token-Level Optimal Transport in a Language-Agnostic Space
掲載ID:
acl-anthology:2026.emnlp-main.933 - From Anonymous Speaker Seeds to Consistent Characters: Zero-Shot Manga Speaker Attribution
掲載ID:
acl-anthology:2026.emnlp-main.2632 - How Well Can LLMs Simulate Real Learner Evaluations of Educational Feedback?
掲載ID:
acl-anthology:2026.emnlp-main.1378 - LEAP: Learning Edit-Adaptable Parameters for Multi-Hop Knowledge Propagation
掲載ID:
acl-anthology:2026.emnlp-main.2150 - MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga Generation
掲載ID:
acl-anthology:2026.emnlp-main.263 - Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning
掲載ID:
acl-anthology:2026.emnlp-main.2575 - MobQA: A Benchmark Dataset for Semantic Understanding of Human Mobility Data through Question Answering
掲載ID:
acl-anthology:2026.emnlp-main.2223 - Overfitting Mitigation via Singular Value Decomposition in Minimum Bayes Risk Decoding
掲載ID:
acl-anthology:2026.emnlp-main.2570 - Persona-CAPS: Controllable and Auditable LLM Personality via Retrieval over Situation–Behavior Contingencies
掲載ID:
acl-anthology:2026.emnlp-main.1495 - Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks
掲載ID:
acl-anthology:2026.emnlp-main.2033 - Rethinking Diffusion Large Language Models via Time-aware Weighting and Block-oriented Refinements
掲載ID:
acl-anthology:2026.emnlp-main.1836 - Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective
掲載ID:
acl-anthology:2026.emnlp-main.2265 - SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification
掲載ID:
acl-anthology:2026.emnlp-main.61 - Self-Evolving Optimization of Agentic Systems for Machine Translation
掲載ID:
acl-anthology:2026.emnlp-main.911 - VidOmni-Bench: A Benchmark for Fine-Grained Video Understanding via Spatio-Temporal Event Verification across Complexity and Duration
掲載ID:
acl-anthology:2026.emnlp-main.104 - When Queries Crowd: Diagnosing and Improving Spread-Out Regularization for Text Embeddings
掲載ID:
acl-anthology:2026.emnlp-main.1585
2025年
- A Statistical and Multi-Perspective Revisiting of the Membership Inference Attack in Large Language Models
掲載ID:
acl-anthology:2025.acl-long.1114 - A-TASC: Asian TED-Based Automatic Subtitling Corpus
掲載ID:
acl-anthology:2025.acl-long.157 - ACT: Knowledgeable Agents to Design and Perform Complex Tasks
掲載ID:
acl-anthology:2025.acl-long.823 - Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition
掲載ID:
acl-anthology:2025.acl-long.462 - Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decoding
掲載ID:
acl-anthology:2025.acl-long.1410 - Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization
掲載ID:
acl-anthology:2025.acl-long.615 - GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking
掲載ID:
acl-anthology:2025.acl-long.729 - If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?
掲載ID:
acl-anthology:2025.acl-long.483 - Information Locality as an Inductive Bias for Neural Language Models
掲載ID:
acl-anthology:2025.acl-long.1357 - MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models
掲載ID:
acl-anthology:2025.acl-long.342 - Neuron Empirical Gradient: Discovering and Quantifying Neurons’ Global Linear Controllability
掲載ID:
acl-anthology:2025.acl-long.1041 - Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling
掲載ID:
acl-anthology:2025.acl-long.87 - Targeted Syntactic Evaluation for Grammatical Error Correction
掲載ID:
acl-anthology:2025.acl-long.1026 - Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding
掲載ID:
acl-anthology:2025.acl-long.1488 - Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models
掲載ID:
acl-anthology:2025.acl-long.326 - Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?
掲載ID:
acl-anthology:2025.emnlp-main.538 - Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset
掲載ID:
acl-anthology:2025.emnlp-main.874 - MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation
掲載ID:
acl-anthology:2025.emnlp-main.79 - Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality
掲載ID:
acl-anthology:2025.emnlp-main.1138東京科学大学 / 名古屋工業大学 / 奈良先端科学技術大学院大学 / 東京大学
- OMS: On-the-fly, Multi-Objective, Self-Reflective Ad Keyword Generation via LLM Agent
掲載ID:
acl-anthology:2025.emnlp-main.938 - ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA
掲載ID:
acl-anthology:2025.emnlp-main.202 - Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models
掲載ID:
acl-anthology:2025.emnlp-main.74 - SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition
掲載ID:
acl-anthology:2025.emnlp-main.19 - TactfulToM: Do LLMs have the Theory of Mind ability to understand White Lies?
掲載ID:
acl-anthology:2025.emnlp-main.1272 - Thinking Out Loud: Do Reasoning Models Know When They’re Right?
掲載ID:
acl-anthology:2025.emnlp-main.73 - Analyzing the Inner Workings of Transformers in Compositional Generalization
掲載ID:
acl-anthology:2025.naacl-long.432 - JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation
掲載ID:
acl-anthology:2025.naacl-long.43 - Language Models can Categorize System Inputs for Performance Analysis
掲載ID:
acl-anthology:2025.naacl-long.317 - LegalViz: Legal Text Visualization by Text To Diagram Generation
掲載ID:
acl-anthology:2025.naacl-long.339東京科学大学 / 奈良先端科学技術大学院大学 / 東京大学
- SHADES: Towards a Multilingual Assessment of Stereotypes in Large Language Models
掲載ID:
acl-anthology:2025.naacl-long.600
2024年
- Emergent Word Order Universals from Cognitively-Motivated Language Models
掲載ID:
acl-anthology:2024.acl-long.781 - Evaluating Intention Detection Capability of Large Language Models in Persuasive Dialogues
掲載ID:
acl-anthology:2024.acl-long.90 - Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling
掲載ID:
acl-anthology:2024.acl-long.388 - Unlearning Traces the Influential Training Data of Language Models
掲載ID:
acl-anthology:2024.acl-long.343 - A Multi-Perspective Analysis of Memorization in Large Language Models
掲載ID:
acl-anthology:2024.emnlp-main.627 - Can Language Models Induce Grammatical Knowledge from Indirect Evidence?
掲載ID:
acl-anthology:2024.emnlp-main.1146 - Vision-Language Model Fine-Tuning via Simple Parameter-Efficient Modification
掲載ID:
acl-anthology:2024.emnlp-main.797 - Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?
掲載ID:
acl-anthology:2024.emnlp-main.1008 - Word Alignment as Preference for Machine Translation
掲載ID:
acl-anthology:2024.emnlp-main.188 - Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?
掲載ID:
acl-anthology:2024.naacl-long.447 - Language Model Based Unsupervised Dependency Parsing with Conditional Mutual Information and Grammatical Constraints
掲載ID:
acl-anthology:2024.naacl-long.352 - Media Bias Detection Across Families of Language Models
掲載ID:
acl-anthology:2024.naacl-long.227 - On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons
掲載ID:
acl-anthology:2024.naacl-long.384
2023年
- Early Discovery of Disappearing Entities in Microblogs
掲載ID:
acl-anthology:2023.acl-long.247 - Subset Retrieval Nearest Neighbor Machine Translation
掲載ID:
acl-anthology:2023.acl-long.10 - WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction
掲載ID:
acl-anthology:2023.acl-long.621 - Referring Image Segmentation via Joint Mask Contextual Embedding Learning and Progressive Alignment Network
掲載ID:
acl-anthology:2023.emnlp-main.481 - SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation
掲載ID:
acl-anthology:2023.emnlp-main.249 - Variance Matters: Detecting Semantic Differences without Corpus/Word Alignment
掲載ID:
acl-anthology:2023.emnlp-main.965
2022年
- Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking
掲載ID:
acl-anthology:2022.acl-long.165 - Modeling Syntactic-Semantic Dependency Correlations in Semantic Role Labeling Using Mixture Models
掲載ID:
acl-anthology:2022.acl-long.548 - Pretraining with Artificial Language: Studying Transferable Knowledge in Language Models
掲載ID:
acl-anthology:2022.acl-long.504 - RNSum: A Large-Scale Dataset for Automatic Release Note Generation via Commit Logs Summarization
掲載ID:
acl-anthology:2022.acl-long.597 - mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models
掲載ID:
acl-anthology:2022.acl-long.505 - Character-centric Story Visualization via Visual Planning and Token Alignment
掲載ID:
acl-anthology:2022.emnlp-main.565 - Context Limitations Make Neural Language Models More Human-Like
掲載ID:
acl-anthology:2022.emnlp-main.712 - Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings
掲載ID:
acl-anthology:2022.emnlp-main.490 - Open-domain Video Commentary Generation
掲載ID:
acl-anthology:2022.emnlp-main.495 - PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings
掲載ID:
acl-anthology:2022.emnlp-main.826 - StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning
掲載ID:
acl-anthology:2022.emnlp-main.114 - A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation
掲載ID:
acl-anthology:2022.naacl-main.223 - EASE: Entity-Aware Contrastive Learning of Sentence Embedding
掲載ID:
acl-anthology:2022.naacl-main.284 - Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts
掲載ID:
acl-anthology:2022.naacl-main.104
掲載対象外の論文や未反映の論文は、この一覧には含まれません。