AAAI 2022 accepted papers on Large language models
60 of the 1,319 papers accepted at AAAI 2022 (4.5%) are on Large language models, compared with 4.7% at AAAI 2021. They fall into 5 topics.
See AAAI 2022 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Language, safety and interpretability · 32 papers
- CEM: Commonsense-Aware Empathetic Response Generation (145 citations)
- Towards Fine-Grained Reasoning for Fake News Detection (79 citations)
- DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization (62 citations)
- Protecting Intellectual Property of Language Generation APIs with Lexical Watermark (54 citations)
- Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-training (52 citations)
- Tracing Text Provenance via Context-Aware Lexical Substitution (51 citations)
- Towards Building ASR Systems for the Next Billion Users (50 citations)
- LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification (34 citations)
- Supervising Model Attention with Human Explanations for Robust Natural Language Inference (32 citations)
- InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation (23 citations)
- Sequence-to-Action: Grammatical Error Correction with Action Guided Sequence Generation (22 citations)
- XLM-K: Improving Cross-Lingual Language Model Pre-training with Multilingual Knowledge (21 citations)
and 20 more in the interactive map.
Retrieval and knowledge · 16 papers
- OneRel: Joint Entity and Relation Extraction with One Module in One Step (187 citations)
- ISEEQ: Information Seeking Question Generation Using Dynamic Meta-Information Retrieval and Knowledge Graphs (52 citations)
- StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts (34 citations)
- Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge (30 citations)
- Enhanced Story Comprehension for Large Language Models through Dynamic Document-Based Knowledge Graphs (29 citations)
- Improving Biomedical Information Retrieval with Neural Retrievers (27 citations)
- Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning (22 citations)
- MeTeoR: Practical Reasoning in Datalog with Metric Temporal Operators (21 citations)
- RetGen: A Joint Framework for Retrieval and Grounded Text Generation Modeling (21 citations)
- Braid: Weaving Symbolic and Neural Knowledge into Coherent Logical Explanations (12 citations)
- KID-Review: Knowledge-Guided Scientific Review Generation with Oracle Pre-training (10 citations)
- Hybrid Autoregressive Inference for Scalable Multi-Hop Explanation Regeneration (8 citations)
and 4 more in the interactive map.
Agents, code and math · 9 papers
- TEACh: Task-Driven Embodied Agents That Chat (100 citations)
- Multilingual Code Snippets Training for Program Translation (38 citations)
- Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability (10 citations)
- Compilation of Aggregates in ASP Systems (9 citations)
- Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoning over Text (7 citations)
- A Calculus for Computing Structured Justifications for Election Outcomes (5 citations)
- PlanVerb: Domain-Independent Verbalization and Summary of Task Plans (5 citations)
- Logic Rule Guided Attribution with Dynamic Ablation (4 citations)
- From Actions to Programs as Abstract Actual Causes (1 citation)
