"One-Size-Fits-All"? Examining Expectations around What Constitute "Fair" or "Good" NLG System Behaviors
Comments 36 pages, 24 figures, NAACL 2024
期刊&会议
NAACL
North American Chapter of the Association for Computational Linguistics · 会议 · Natural Language Processing
UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Tracking
Comments Accepted to Findings of NAACL 2024
DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers
Comments Accepted to Findings of NAACL 2024
UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions
Comments Accepted at NAACL 2024
Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis
Comments Accepted to NAACL 2024 Main Conference
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
Comments Accepted to NAACL 2024. Project page: https://poison-llm.github.io
Language Models Implement Simple Word2Vec-style Vector Arithmetic
Comments NAACL
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
Comments NAACL 2024
Backdoor Attack on Multilingual Machine Translation
Comments NAACL main long paper
Low-resource neural machine translation with morphological modeling
Comments NAACL Findings 2024
On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL
Comments to appear at NAACL 2024
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors
Comments Accepted by NAACL 2024 Main Conference
Emergent Abilities in Reduced-Scale Generative Language Models
Comments 16 pages, 4 figures. Accepted to NAACL 2024 Findings
OSCaR: Object State Captioning and State Change Representation
Comments NAACL 2024
Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries
Comments NAACL 2024
Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence
Comments Accepted by NAACL 2024 main conference
Take One Step at a Time to Know Incremental Utility of Demonstration: An Analysis on Reranking for Few-Shot In-Context Learning
Comments Accepted as a long paper at NAACL 2024
Pregnant Questions: The Importance of Pragmatic Awareness in Maternal Health Question Answering
Comments Accepted to NAACL 2024
Effective Large Language Model Adaptation for Improved Grounding and Citation Generation
Comments NAACL 2024
Grounding Gaps in Language Model Generations
Comments NAACL 2024; 18 pages, 2 figures
Anti-LM Decoding for Zero-shot In-context Machine Translation
Comments Accepted to NAACL Findings 2024
Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications
Comments NAACL 2024 (Main Conference)
Automatic Pair Construction for Contrastive Post-training
Comments NAACL 2024 (Findings)
Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?
Comments To appear in NAACL 2024
From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
Comments Accepted by NAACL 2024 Main Conference
Dissecting Paraphrases: The Impact of Prompt Syntax and supplementary Information on Knowledge Retrieval from Pretrained Language Models
Comments Accepted for NAACL 2024
Team UTSA-NLP at SemEval 2024 Task 5: Prompt Ensembling for Argument Reasoning in Civil Procedures with GPT4
Comments Accepted to SemEval@NAACL 2024
SGSH: Stimulate Large Language Models with Skeleton Heuristics for Knowledge Base Question Generation
Comments Accepted by NAACL 2024 Findings
SCANNER: Knowledge-Enhanced Approach for Robust Multi-modal Named Entity Recognition of Unseen Entities
Comments 13 pages, 7 figures, NAACL 2024
Sentence-level Media Bias Analysis with Event Relation Graph
Comments Accepted to NAACL 2024
