Strings from the Library of Babel: Random Sampling as a Strong Baseline for Prompt Optimisation
Comments Accepted to NAACL 2024. The code is publicly available at https://github.com/yaolu/random-prompt
期刊&会议
NAACL
North American Chapter of the Association for Computational Linguistics · 会议 · Natural Language Processing
Shears: Unstructured Sparsity with Neural Low-rank Adapter Search
Comments 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (Industry Track)
Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training
Comments NAACL Findings 2024
GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models
Comments 14 pages, Findings of NAACL 2024, Spotlight on TGL@NeurIPS2023
TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition
Comments Accepted to NAACL 2024 (long, main)
A Measure for Transparent Comparison of Linguistic Diversity in Multilingual NLP Data Sets
Comments Accepted to NAACL 2024 Findings
The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text
Comments Accepted to NAACL 2024 Findings
Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval
Comments Accepted at NAACL 2024. Data released at https://github.com/google-research-datasets/swim-ir
X-PARADE: Cross-Lingual Textual Entailment and Information Divergence across Paragraphs
Comments To be published in NAACL 2024
Context Does Matter: Implications for Crowdsourced Evaluation Labels in Task-Oriented Dialogue Systems
Comments Accepted at NAACL 2024 Findings
ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models
Comments Accepted by NAACL-2024
Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?
Comments Accepted by NAACL 2024 (Industry Track). The first two authors contributed equally to this work
MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning
Comments Accepted to NAACL 2024
Psychometric Predictive Power of Large Language Models
Comments 23 pages; Findings of NAACL 2024
Evaluating the Deductive Competence of Large Language Models
Comments 17 pages, 7 figures, accepted to NAACL 2024
Bridging the Gap between Different Vocabularies for LLM Ensemble
Comments Accepted to the main conference of NAACL 2024
The Effect of Data Partitioning Strategy on Model Generalizability: A Case Study of Morphological Segmentation
Comments Accepted to 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (16 pages including 9 tables and 1 figure)
When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models
Comments NAACL 2024 Findings paper (Camera-Ready Version)
EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM
Comments Accepted by NAACL 2024 Industry Track
Toward Informal Language Processing: Knowledge of Slang in Large Language Models
Comments Accepted to NAACL 2024 main conference
A Novel Paradigm Boosting Translation Capabilities of Large Language Models
Comments Accepted in NAACL 2024
Rectifying Demonstration Shortcut in In-Context Learning
Comments NAACL 2024
PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck
Comments Findings of NAACL 2024 (long paper)
ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models
Comments Accepted to NAACL 2024 main conference
X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects
Comments NAACL 2024 Main Conference. 20 pages, 6 figures, 17 tables
Adapting Fake News Detection to the Era of Large Language Models
Comments Accept to NAACL 2024 Findings
Contextual Label Projection for Cross-Lingual Structured Prediction
Comments Accepted at NAACL 2024
Can Public Large Language Models Help Private Cross-device Federated Learning?
Comments Published at Findings of NAACL 2024
Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System
Comments NAACL Findings 2022, see https://aclanthology.org/2022.findings-naacl.43
VertAttack: Taking advantage of Text Classifiers' horizontal vision
Comments 14 pages, 4 figures, accepted to NAACL 2024
