AAAI 2023 accepted papers on Large language models
125 of the 2,023 papers accepted at AAAI 2023 (6.2%) are on Large language models, compared with 4.5% at AAAI 2022. They fall into 6 topics.
See AAAI 2023 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
AI and society · 52 papers
- Toward a Perspectivist Turn in Ground Truthing for Predictive Computing (87 citations)
- AI Audit: A Card Game to Reflect on Everyday AI Systems (34 citations)
- Literacy and STEM Teachers Adapt AI Ethics Curriculum (28 citations)
- Build-a-Bot: Teaching Conversational AI Using a Transformer-Based Intent Recognition and Question Answering Architecture (23 citations)
- An Analysis of Engineering Students’ Responses to an AI Ethics Scenario (18 citations)
- Modeling Human Trust and Reliance in AI-Assisted Decision Making: A Markovian Approach (18 citations)
- MoMusic: A Motion-Driven Human-AI Collaborative Music Composition and Performing System (18 citations)
- Scratch for Sports: Athletic Drills as a Platform for Experiencing, Understanding, and Developing AI-Driven Apps (14 citations)
- Beyond Black-Boxes: Teaching Complex Machine Learning Ideas through Scaffolded Interactive Activities (13 citations)
- Demo Alleviate: Demonstrating Artificial Intelligence Enabled Virtual Assistance for Telehealth: The Mental Health Case (11 citations)
- AI Made by Youth: A Conversational AI Curriculum for Middle School Summer Camps (10 citations)
- Develop AI Teaching and Learning Resources for Compulsory Education in China (10 citations)
and 40 more in the interactive map.
Language, safety and interpretability · 32 papers
- A Holistic Approach to Undesired Content Detection in the Real World (119 citations)
- Real or Fake Text?: Investigating Human Ability to Detect Boundaries between Human-Written and Machine-Generated Text (49 citations)
- NL2LTL – a Python Package for Converting Natural Language (NL) Instructions to Linear Temporal Logic (LTL) Formulas (48 citations)
- Solving Math Word Problems concerning Systems of Equations with GPT-3 (32 citations)
- ADEPT: A DEbiasing PrompT Framework (28 citations)
- IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian Languages (24 citations)
- Learning to Memorize Entailment and Discourse Relations for Persona-Consistent Dialogues (23 citations)
- MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsing (22 citations)
- A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding (19 citations)
- Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness (12 citations)
- H-AES: Towards Automated Essay Scoring for Hindi (12 citations)
- MIGA: A Unified Multi-Task Generation Framework for Conversational Text-to-SQL (12 citations)
and 20 more in the interactive map.
Retrieval and knowledge · 20 papers
- Contrastive Learning Reduces Hallucination in Conversations (63 citations)
- Factual and Informative Review Generation for Explainable Recommendation (17 citations)
- DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data (16 citations)
- Enabling Knowledge Refinement upon New Concepts in Abductive Learning (12 citations)
- Multi-Aspect Explainable Inductive Relation Prediction by Sentence Transformer (12 citations)
- LIQUID: A Framework for List Question Answering Dataset Generation (11 citations)
- Question Decomposition Tree for Answering Complex Questions over Knowledge Bases (11 citations)
- CP-Rec: Contextual Prompting for Conversational Recommender Systems (10 citations)
- Learning by Applying: A General Framework for Mathematical Reasoning via Enhancing Explicit Knowledge Learning (7 citations)
- QA Is the New KR: Question-Answer Pairs as Knowledge Bases (5 citations)
- GLUECons: A Generic Benchmark for Learning under Constraints (4 citations)
- KPT: Keyword-Guided Pre-training for Grounded Dialog Generation (4 citations)
and 8 more in the interactive map.
Agents, code and math · 16 papers
- Repair Is Nearly Generation: Multilingual Program Repair with LLMs (109 citations)
- On Grounded Planning for Embodied Tasks with Language Models (21 citations)
- Foundation Model for Material Science (19 citations)
- Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion (7 citations)
- Generalizing Math Word Problem Solvers via Solution Diversification (7 citations)
- Probabilistic Programs as an Action Description Language (7 citations)
- Relational Program Synthesis with Numerical Reasoning (4 citations)
- Towards Hybrid Automation by Bootstrapping Conversational Interfaces for IT Operation Tasks (3 citations)
- Formally Verified SAT-Based AI Planning (2 citations)
- Neurosymbolic Reasoning and Learning with Restricted Boltzmann Machines (2 citations)
- Untangled: A Complete Dynamic Topological Logic (2 citations)
- Automatically Verifying Expressive Epistemic Properties of Programs (1 citation)
and 4 more in the interactive map.
Instruction and fine-tuning · 4 papers
- Prompt-Augmented Linear Probing: Scaling beyond the Limit of Few-Shot In-Context Learners (10 citations)
- Prototypical Fine-Tuning: Towards Robust Performance under Varying Data Sizes (3 citations)
- A Data Source for Reasoning Embodied Agents
- A Generative Approach for Script Event Prediction via Contrastive Fine-Tuning