CodeSCM: Causal Analysis for Multi-Modal Code Generation
Comments Accepted to NAACL 2025
期刊&会议
NAACL
North American Chapter of the Association for Computational Linguistics · 会议 · Natural Language Processing
Aligning Black-box Language Models with Human Judgments
Comments Accepted for publication at NAACL 2025 (Findings)
Commonality and Individuality! Integrating Humor Commonality with Speaker Individuality for Humor Recognition
Comments Accepted by NAACL 2025
SSMLoRA: Enhancing Low-Rank Adaptation with State Space Model
Comments Has been accepted by NAACL 2025
Verifiable Format Control for Large Language Model Generations
Comments To appear at Findings of NAACL 2025
Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detection
Comments Accepted to NAACL Findings 2025
Can LLMs Convert Graphs to Text-Attributed Graphs?
Comments Accepted by NAACL 25 Main Conference
MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation
Comments Accepted by NAACL 2025 main conference. Camera-ready version
Mastering the Craft of Data Synthesis for CodeLLMs
Comments Accepted at NAACL 2025
VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning
Comments Accepted at NAACL 2025 main conference
LLM The Genius Paradox: A Linguistic and Math Expert's Struggle with Simple Word-based Counting Problems
Comments NAACL 2025
Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answering
Comments NAACL 2025 Main
Grounding Fallacies Misrepresenting Scientific Publications in Evidence
Comments Accepted to NAACL 2025
How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments
Comments NAACL 2025 main
From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning
Comments NAACL 2025
Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs
Comments Accepted at NAACL 2025
Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data
Comments Accepted to NAACL 2025, main conference. 20 pages, 10 figures, 10 tables
Sports and Women's Sports: Gender Bias in Text Generation with Olympic Data
Comments NAACL 2025
Probe-Free Low-Rank Activation Intervention
Comments Accepted by NAACL 2025
Efficient Nearest Neighbor based Uncertainty Estimation for Natural Language Processing Tasks
Comments Accepted at Findings of NAACL 2025
HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing
Comments NAACL 2025 Main Conference
A comprehensive survey of contemporary Arabic sentiment analysis: Methods, Challenges, and Future Directions
Comments Paper accepted to NAACL 2025
Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale Evaluation
Comments Accepted to NAACL 2025
Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval
Comments NAACL 2025
Language Models "Grok" to Copy
Comments NAACL 2025 main conference, short paper
Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generation
Comments NAACL 2025 main
Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models
Comments NAACL 2025 Findings
Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales
Comments Pre-print for a paper accepted to findings of NAACL 2025
DOLFIN -- Document-Level Financial test set for Machine Translation
Comments To be published in NAACL 2025 Findings
Yeah, Un, Oh: Continuous and Real-time Backchannel Prediction with Fine-tuning of Voice Activity Projection
Comments This paper has been accepted for presentation at the main conference of 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025) and represents the author's version of the work
