ACL 2024

2,541 papers

Top Research Directions

Research directions most represented by ACL 2024 papers.

Shifting from Static Benchmarks to Dynamic Evaluation 76
Factual Inaccuracy and Hallucination in Large Language Models 65
Grounding Language Models with External Knowledge Retrieval 49
Understanding Prompt Sensitivity in Language Models 40
Mitigating Data Scarcity in Low Resource Language Processing 40
Task Activation via In Context Demonstrations 33
Iterative Retrieval Augmented Generation for Multi Hop Reasoning 32
Evaluating Generative AI with Large Language Models 32
Intermediate Reasoning Chains for Deliberative Inference 32
Contextual Distraction and Noise Sensitivity in Language Models 31
The Mechanics of Bias Amplification in Language Models 31
Adapting Natural Language Processing to Dialectal Diversity 29
Overcoming Temporal Knowledge Obsolescence in Language Models 27
The Language Bias of English Centric Benchmarks 27
Why Long-Context Language Models Get Lost in the Middle 26

Top Authors

AuthorPapers
Min Zhang34
Xuanjing Huang18
Maosong Sun17
Fandong Meng16
Jie Zhou15
Zhiyuan Liu14
Bing Qin13
Iryna Gurevych12
Le Sun12
Ruifeng Xu12
Xipeng Qiu12
Dahua Lin11
hai zhao11
Rui Yan11
Zhou Zhao11
Fei Huang10
Ji-Rong Wen10
Liang Ding10
Min Yang10
Tat-Seng Chua10

Impactful Papers

Papers from ACL 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
LooGLE: Can Long-Context Language Models Understand Long Contexts?
Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling
LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
LoRA Meets Dropout under a Unified Framework
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning
LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild
Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation
Low Resource ICD Coding of Hospital Discharge Summaries
LPNL: Scalable Link Prediction with Large Language Models
LRQuant: Learnable and Robust Post-Training Quantization for Large Language Models
LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting
LT4SG@SMM4H’24: Tweets Classification for Digital Epidemiology of Childhood Health Outcomes Using Pre-Trained Language Models
M³AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset
M³CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought
M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection
M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models
Machine-Generated Text Localization
Machine Translation Through Cultural Texts: Can Verses and Prose Help Low-Resource Indigenous Models?
Machine Unlearning of Pre-trained Large Language Models
MAGE: Machine-generated Text Detection in the Wild
Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners
Making Harmful Behaviors Unlearnable for Large Language Models
Making Long-Context Language Models Better Multi-Hop Reasoners
ManWav: The First Manchu ASR Model
MapCoder: Multi-Agent Code Generation for Competitive Problem Solving
MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation
MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models
MAPO: Advancing Multilingual Reasoning through Multilingual-Alignment-as-Preference Optimization
MAP's not dead yet: Uncovering true language model modes by conditioning away degeneracy
Marathon: A Race Through the Realm of Long Context with Large Language Models
MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
MaskLID: Code-Switching Language Identification through Iterative Masking
Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge
Match More, Extract Better! Hybrid Matching Model for Open Domain Web Keyphrase Extraction
MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark
\mathcal XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts
MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sources
MAVEN-ARG: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation
Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends
MBIAS: Mitigating Bias in Large Language Models While Retaining Context
MC²: Towards Transparent and Culturally-Aware NLP for Minority Languages in China
mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models
mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans

« prev Page 29/51 next »