natural language processing
A field of AI focused on the interaction between computers and human languages, enabling machines to understand, interpret, and generate text.
- A Circular Argument: Does RoPE need to be Equivariant for Vision?
- A Semantic Parsing Framework for End-to-End Time Normalization
- AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
- Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models
- Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks
- Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
- ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World
- Cypher-RI: Reinforcement Learning for Integrating Schema Selection into Cypher Generation
- FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling
- HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of Experts
- KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
- Learning Shared Representations from Unpaired Data
- LexiCon: a Benchmark for Planning under Temporal Constraints in Natural Language
- Measuring what Matters: Construct Validity in Large Language Model Benchmarks
- On Learning Verifiers and Implications to Chain-of-Thought Reasoning
- On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study
- OrdShap: Feature Position Importance for Sequential Black-Box Models
- Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention
- SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL
- SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs
- Sampled Estimators For Softmax Must Be Biased
- Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity
- ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling
- ShortListing Model: A Streamlined Simplex Diffusion for Discrete Variable Generation
- StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training
- Wavy Transformer
- Zero-Shot Performance Prediction for Probabilistic Scaling Laws