Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper
Comments Accepted to EMNLP Findings 2024
期刊&会议
EMNLP
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis
Comments Accepted to EMNLP-24
DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questions
Comments EMNLP 2024: The 2024 Conference on Empirical Methods in Natural Language Processing
Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models
Comments EMNLP 2024 main, 24 pages, 16 figures
Can AI Relate: Testing Large Language Model Response for Mental Health Support
Comments EMNLP 2024 Findings
Latent Concept-based Explanation of NLP Models
Comments Accepted by EMNLP 2024 Main Conference
SWAG: Storytelling With Action Guidance
Comments EMNLP Findings 2024
Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals
Comments Findings of EMNLP 2024
Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models
Comments Accepted to EMNLP 2024 Main Conference. Project website: https://feiwang96.github.io/DataAdvisor/
Grounding Partially-Defined Events in Multimodal Data
Comments Preprint; 9 pages; 2024 EMNLP Findings
Precise Model Benchmarking with Only a Few Observations
Comments To appear at EMNLP 2024
Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
Comments EMNLP 2024 (Long, Main). Project page: https://ytaek-oh.github.io/fsc-clip
Beyond Correlation: Interpretable Evaluation of Machine Translation Metrics
Comments Accepted at EMNLP 2024 Main Conference. 26 pages
Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models
Comments Accepted at EMNLP 2024
ZEBRA: Zero-Shot Example-Based Retrieval Augmentation for Commonsense Question Answering
Comments Accepted at EMNLP 2024 Main Conference
Activation Scaling for Steering and Interpreting Language Models
Comments Findings of the Association for Computational Linguistics: EMNLP 2024
Leveraging Grammar Induction for Language Understanding and Generation
Comments EMNLP 2024 Findings
Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge
Comments accepted by EMNLP 2024, main conference
Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering
Comments Accepted at Findings of EMNLP 2024. Camera-ready version
The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead?
Comments Accepted to EMNLP Main 2024. First two authors contributed equally
Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning
Comments EMNLP'24 Findings
Contrastive Learning to Improve Retrieval for Real-world Fact Checking
Comments EMNLP 2024 FEVER Workshop
Control Large Language Models via Divide and Conquer
Comments EMNLP 2024
How Does the Disclosure of AI Assistance Affect the Perceptions of Writing?
Comments EMNLP 2024. arXiv admin note: text overlap with arXiv:2403.12004
RevMUX: Data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference
Comments EMNLP 2024 Main Conference
Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis
Comments Accepted to EMNLP Findings 2024
Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information
Comments Accepted by EMNLP 2024 Findings
CAPEEN: Image Captioning with Early Exits and Knowledge Distillation
Comments To appear in EMNLP (finding) 2024
DAdEE: Unsupervised Domain Adaptation in Early Exit PLMs
Comments To appear in EMNLP (findings) 2024
Entity Insertion in Multilingual Linked Corpora: The Case of Wikipedia
Comments EMNLP 2024; 24 pages; 62 figures
