AAAI 2024 accepted papers on Large language models
239 of the 2,864 papers accepted at AAAI 2024 (8.3%) are on Large language models, compared with 6.2% at AAAI 2023. They fall into 7 topics.
See AAAI 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Language, safety and interpretability · 86 papers
- Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection (221 citations)
- AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head (114 citations)
- Enhancing Job Recommendation through LLM-Based Generative Adversarial Networks (82 citations)
- Bootstrapping Large Language Models for Radiology Report Generation (72 citations)
- MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators (69 citations)
- Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations (68 citations)
- Automatic Short Answer Grading for Finnish with ChatGPT (55 citations)
- MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records (49 citations)
- Detecting AI-Generated Code Assignments Using Perplexity of Large Language Models (45 citations)
- Large Language Models Are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales (44 citations)
- Fluctuation-Based Adaptive Structured Pruning for Large Language Models (43 citations)
- OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples (40 citations)
and 74 more in the interactive map.
AI and society · 61 papers
- MemoryBank: Enhancing Large Language Models with Long-Term Memory (201 citations)
- Students’ Perceptions and Preferences of Generative Artificial Intelligence Feedback for Programming (46 citations)
- Co-designing AI Education Curriculum with Cross-Disciplinary High School Teachers (37 citations)
- Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis (35 citations)
- Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties (31 citations)
- An Effectiveness Study of Teacher-Led AI Literacy Curriculum in K-12 Classrooms (29 citations)
- From Statistical Relational to Neuro-Symbolic Artificial Intelligence (21 citations)
- Build Your Own Robot Friend: An Open-Source Learning Module for Accessible and Engaging AI Education (20 citations)
- Merging AI Incidents Research with Political Misinformation Research: Introducing the Political Deepfakes Incidents Database (19 citations)
- When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming (19 citations)
- Your Prompt Is My Command: On Assessing the Human-Centred Generality of Multimodal Models (Abstract Reprint) (18 citations)
- From Consumers to Critical Users: Prompty, an AI Literacy Tool for High School Students (15 citations)
and 49 more in the interactive map.
Retrieval and knowledge · 39 papers
- Benchmarking Large Language Models in Retrieval-Augmented Generation (384 citations)
- Knowledge Graph Prompting for Multi-Document Question Answering (155 citations)
- Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models (81 citations)
- FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering (77 citations)
- Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-Based Retrofitting (77 citations)
- Graph Neural Prompting with Large Language Models (58 citations)
- CyberQ: Generating Questions and Answers for Cybersecurity Education Using Knowledge Graph-Augmented LLMs (37 citations)
- Improving Automatic VQA Evaluation Using Large Language Models (36 citations)
- MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models (36 citations)
- LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs (32 citations)
- Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation (27 citations)
- MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA (22 citations)
and 27 more in the interactive map.
Agents, code and math · 32 papers
- ExpeL: LLM Agents Are Experiential Learners (123 citations)
- Generalized Planning in PDDL Domains with Pretrained Large Language Models (71 citations)
- Can LLM Replace Stack Overflow? A Study on Robustness and Reliability of Large Language Model Code Generation (63 citations)
- SayCanPay: Heuristic Planning with Large Language Models Using Learnable Domain Knowledge (33 citations)
- SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research (30 citations)
- Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark (24 citations)
- Improving Knowledge Extraction from LLMs for Task Learning through Agent Analysis (19 citations)
- PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine (18 citations)
- Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum (16 citations)
- Generating Novel Leads for Drug Discovery Using LLMs with Logical Feedback (15 citations)
- TaskLAMA: Probing the Complex Task Understanding of Language Models (14 citations)
- Benchmarking Large Language Models on Controllable Generation under Diversified Instructions (8 citations)
and 20 more in the interactive map.
Instruction and fine-tuning · 10 papers
- Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-World Multi-Turn Dialogue (110 citations)
- EcomGPT: Instruction-Tuning Large Language Models with Chain-of-Task Tasks for E-commerce (28 citations)
- Fine-Tuning Large Language Model Based Explainable Recommendation with Explainable Quality Reward (28 citations)
- Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following (13 citations)
- Teaching Large Language Models to Translate with Comparison (13 citations)
- SentinelLMs: Encrypted Input Adaptation and Fine-Tuning of Language Models for Private and Secure Inference (7 citations)
- Biases Mitigation and Expressiveness Preservation in Language Models: A Comprehensive Pipeline (Student Abstract) (6 citations)
- Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning (6 citations)
- Amplifying Diversity and Quality in Commonsense Knowledge Graph Completion (Student Abstract) (4 citations)
- DINGO: Towards Diverse and Fine-Grained Instruction-Following Evaluation (2 citations)
Reasoning and chain of thought · 9 papers
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models (512 citations)
- KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning (38 citations)
- T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Large Language Model Signals for Science Question Answering (37 citations)
- Chain-of-Thought Improves Text Generation with Citations in Large Language Models (15 citations)
- ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference (9 citations)
- MindMap: Constructing Evidence Chains for Multi-Step Reasoning in Large Language Models (8 citations)
- Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data (8 citations)
- Get an A in Math: Progressive Rectification Prompting (3 citations)
- A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students’ Formative Assessment Responses in Science