How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models
Comments Accepted by NAACL 2025
期刊&会议
NAACL
North American Chapter of the Association for Computational Linguistics · 会议 · Natural Language Processing
Atoxia: Red-teaming Large Language Models with Target Toxic Answers
Comments Accepted to Findings of NAACL-2025
Entropy-Based Decoding for Retrieval-Augmented Large Language Models
Comments NAACL 2025 Main Conference
PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection
Comments This is a camera-ready version of NAACL 2025
GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasets
Comments The first two authors contributed equally to this work. This paper has been accepted by NAACL 2025. GraphEval36K is available at https://grapheval36k.github.io/
Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model
Journal ref NAACL 2025
Towards Rationality in Language and Multimodal Agents: A Survey
Comments This paper has been accepted to the NAACL 2025 Main
The Point of View of a Sentiment: Towards Clinician Bias Detection in Psychiatric Notes
Comments Oral presentation at NAACL 2024 Queer in AI Workshop
QuaLLM: An LLM-based Framework to Extract Quantitative Insights from Online Forums
Comments Accepted to NAACL Findings (2025), cite appropriately. Preliminary version presented at CHI LLM as Research Tools Workshop (2024)
Understanding Figurative Meaning through Explainable Visual Entailment
Comments NAACL 2025 Main Conference
GINopic: Topic Modeling with Graph Isomorphism Network
Comments Accepted as a long paper for NAACL 2024 main conference
Learning to Substitute Words with Model-based Score Ranking
Comments Accepted at NAACL 2025 (main, long)
Language Models Largely Exhibit Human-like Constituent Ordering Preferences
Comments NAACL 2025 Main Conference
Evaluating the Prompt Steerability of Large Language Models
Comments Short version appeared at the Pluralistic Alignment workshop at NeurIPS 2024; extended version appeared at NAACL 2025
Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?
Comments NAACL 2025 Main
Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
Comments NAACL Main 2025
Exploring the Potential of Large Language Models for Heterophilic Graphs
Comments Accepted by NAACL 2025
Towards Federated Low-Rank Adaptation of Language Models with Rank Heterogeneity
Comments NAACL 2025
THOUGHTSCULPT: Reasoning with Intermediate Revision and Search
Comments Accepted to NAACL 2025 Findings. Code and data available at https://github.com/cyzus/thoughtsculpt
STAR: Spectral Truncation and Rescale for Model Merging
Comments Accepted to NAACL 2025
Can Post-Training Quantization Benefit from an Additional QLoRA Integration?
Comments Accepted to NAACL 2025 Industry Track
AI-VERDE: A Gateway for Egalitarian Access to Large Language Model-Based Resources For Educational Institutions
Comments 7 Pages, includes appendix. Submitted to NAACL System demonstrations track 2025
From Argumentation to Deliberation: Perspectivized Stance Vectors for Fine-grained (Dis)agreement Analysis
Comments Accepted at NAACL Findings 2025
CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking
Comments Accepted to NAACL-25
Syntriever: How to Train Your Retriever with Synthetic Data from LLMs
Comments the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), Findings, Accepted
Echoes of Discord: Forecasting Hater Reactions to Counterspeech
Comments NAACL 2025 Findings
Evaluating and Improving Graph to Text Generation with Large Language Models
Comments NAACL 2025
Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey
Comments Accepted to NAACL 2025 Findings
Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models
Comments NAACL 2025 (Findings)
GroundCocoa: A Benchmark for Evaluating Compositional & Conditional Reasoning in Language Models
Comments 16 pages, 17 figures, 3 tables. Accepted to NAACL 2025 (Main)
