TCProF: Time-Complexity Prediction SSL Framework
Comments 26 pages, 13 figures, This paper has been accepted to NAACL 2025
期刊&会议
NAACL
North American Chapter of the Association for Computational Linguistics · 会议 · Natural Language Processing
Towards Automatic Evaluation for Image Transcreation
Comments To be presented at NAACL 2025
Large Language Models and Causal Inference in Collaboration: A Survey
Comments Findings of the Association for Computational Linguistics: NAACL 2025
EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
Comments Accepted to the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025)
Automatically Generating Chinese Homophone Words to Probe Machine Translation Estimation Systems
Comments Accepted to the 10th Workshop on Noisy and User-generated Text at NAACL 2025
Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models
Comments Accepted to the 6th Workshop on Insights from Negative Results in NLP at NAACL 2025
Using Contextually Aligned Online Reviews to Measure LLMs' Performance Disparities Across Language Varieties
Comments Accepted by 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), theme track
Measuring memorization in language models via probabilistic extraction
Comments NAACL 25
MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration
Comments NAACL 2025, 18 pages. Code: https://github.com/meetdavidwan/mammrefine
LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones?
Comments Accepted to the C3NLP workshop (Co-located with NAACL 2025)
LLM Reasoning Engine: Specialized Training for Enhanced Mathematical Reasoning
Comments Accepted to NAACL 2025 KnowledgeNLP
JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation
Comments Accepted at NAACL 2025. Project page: https://mmmu-japanese-benchmark.github.io/JMMMU/
See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias
Comments Accepted to NAACL 2025 Main
Towards AI-assisted Academic Writing
Comments accepted to NAACL 2025 Workshop on AI for Scientific Discovery
MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG
Comments NAACL 2025
OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews
Comments NAACL 2025 System Demonstrations Track (Camera-ready version) Demo: https://huggingface.co/spaces/maxidl/openreviewer Model: https://huggingface.co/maxidl/Llama-OpenReviewer-8B
Fair Summarization: Bridging Quality and Diversity in Extractive Summaries
Comments Accepted at AFLME@NeurIPS 2024 (non-archival) & C3NLP@NAACL 2025 (publication)
TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods
Comments Accepted to the NAACL PrivateNLP 2025 Workshop
Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
Comments Accepted at NAACL 2025 (Industry track)
From Guessing to Asking: An Approach to Resolving the Persona Knowledge Gap in LLMs during Multi-Turn Conversations
Comments 12 pages, 1 Figure, Oral Presentation at NAACL 2025
SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression
Comments NAACL 2025; Code available at AIoT-MLSys-Lab/SVD-LLM" target="_blank" rel="noopener">https://github.com/AIoT-MLSys-Lab/SVD-LLM
Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models
Comments NAACL 2025
LLMs for Translation: Historical, Low-Resourced Languages and Contemporary AI Models
Comments Accepted to LaTeCH-CLfL 2025, held in conjunction with NAACL 2025
Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models
Comments Accepted at the NAACL 2025 Main Conference
Beemo: Benchmark of Expert-edited Machine-generated Outputs
Comments Accepted to NAACL 2025
ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis
Comments Accepted by NAACL 2025
Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step
Comments Accepted by Findings of NAACL 2025
Chain of Evidences and Evidence to Generate: Prompting for Context Grounded and Retrieval Augmented Reasoning
Comments Accepted at NAACL KnowledgeNLP 2025
An LLM-Based Approach for Insight Generation in Data Analysis
Comments Accepted for publication at NAACL 2025
Cerebrum (AIOS SDK): A Platform for Agent Development, Deployment, Distribution, and Discovery
Comments Accepted to the 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) - System Demonstration Track
