| CREST: A Joint Framework for Rationalization and Counterfactual Text Generation | May 26, 2023 | counterfactualData Augmentation | CodeCode Available | 0 |
| STL: Surprisingly Tricky Logic (for System Validation) | May 26, 2023 | valid | —Unverified | 0 |
| DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models | May 26, 2023 | Bayesian OptimizationNeural Architecture Search | CodeCode Available | 1 |
| Learning and Leveraging Verifiers to Improve Planning Capabilities of Pre-trained Language Models | May 26, 2023 | valid | —Unverified | 0 |
| Evaluation of Question Generation Needs More References | May 26, 2023 | Question GenerationQuestion-Generation | —Unverified | 0 |
| Superpixelwise Low-Rank Approximation-Based Partial Label Learning for Hyperspectral Image Classification | May 25, 2023 | Hyperspectral Image Classificationimage-classification | CodeCode Available | 0 |
| On the Robustness of Segment Anything | May 25, 2023 | Autonomous VehiclesPrompt Learning | —Unverified | 0 |
| End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes | May 25, 2023 | Bayesian OptimisationInductive Bias | CodeCode Available | 0 |
| Exponential Smoothing for Off-Policy Learning | May 25, 2023 | valid | —Unverified | 0 |
| Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models | May 24, 2023 | Inference AttackMembership Inference Attack | —Unverified | 0 |
| Increasing Probability Mass on Answer Choices Does Not Always Improve Accuracy | May 24, 2023 | In-Context LearningMultiple-choice | CodeCode Available | 0 |
| Short and Straight: Geodesics on Differentiable Manifolds | May 24, 2023 | valid | —Unverified | 0 |
| Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory | May 24, 2023 | nlg evaluationText Generation | CodeCode Available | 1 |
| On Degrees of Freedom in Defining and Testing Natural Language Understanding | May 24, 2023 | Natural Language Understandingvalid | —Unverified | 0 |
| Annotation Imputation to Individualize Predictions: Initial Studies on Distribution Dynamics and Model Predictions | May 24, 2023 | Imputationvalid | CodeCode Available | 0 |
| Uncertainty Quantification over Graph with Conformalized Graph Neural Networks | May 23, 2023 | Conformal PredictionPrediction | CodeCode Available | 1 |
| Deduction under Perturbed Evidence: Probing Student Simulation Capabilities of Large Language Models | May 23, 2023 | Logical ReasoningStrategyQA | —Unverified | 0 |
| Enhanced Fine-grained Motion Diffusion for Text-driven Human Motion Synthesis | May 23, 2023 | Motion Synthesisvalid | —Unverified | 0 |
| Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs | May 23, 2023 | valid | —Unverified | 0 |
| Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning | May 23, 2023 | Code GenerationConstituency Parsing | CodeCode Available | 2 |
| Tight conditions for when the NTK approximation is valid | May 22, 2023 | valid | —Unverified | 0 |
| Many or Few Samples? Comparing Transfer, Contrastive and Meta-Learning in Encrypted Traffic Classification | May 21, 2023 | Contrastive LearningMeta-Learning | —Unverified | 0 |
| A parametric distribution for exact post-selection inference with data carving | May 21, 2023 | valid | CodeCode Available | 0 |
| Logic-Based Benders Decomposition in Answer Set Programming for Chronic Outpatients Scheduling | May 19, 2023 | Schedulingvalid | —Unverified | 0 |
| Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees | May 19, 2023 | counterfactualvalid | CodeCode Available | 0 |
| Generalized Multiple Intent Conditioned Slot Filling | May 18, 2023 | Intent DetectionLanguage Modeling | —Unverified | 0 |
| Wavefield Networked Sensing: Principles, Algorithms and Applications | May 17, 2023 | valid | —Unverified | 0 |
| Generation of 3D Molecules in Pockets via Language Model | May 17, 2023 | 3D Molecule GenerationDrug Design | —Unverified | 0 |
| Complementary Classifier Induced Partial Label Learning | May 17, 2023 | Partial Label Learningvalid | CodeCode Available | 0 |
| Finding an ε-close Variation of Parameters in Bayesian Networks | May 17, 2023 | valid | —Unverified | 0 |
| Score Operator Newton transport | May 16, 2023 | Bayesian Inferencevalid | —Unverified | 0 |
| Learning Linear Embeddings for Non-Linear Network Dynamics with Koopman Message Passing | May 15, 2023 | valid | —Unverified | 0 |
| How Expressive are Spectral-Temporal Graph Neural Networks for Time Series Forecasting? | May 11, 2023 | Graph Neural NetworkTime Series | —Unverified | 0 |
| SMATCH++: Standardized and Extended Evaluation of Semantic Graphs | May 11, 2023 | Semantic SimilaritySemantic Textual Similarity | CodeCode Available | 1 |
| Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge | May 10, 2023 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
| Testing for Overfitting | May 9, 2023 | Holdout Setvalid | CodeCode Available | 0 |
| Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files | May 9, 2023 | valid | —Unverified | 0 |
| Comparing Foundation Models using Data Kernels | May 9, 2023 | BenchmarkingSelf-Supervised Learning | —Unverified | 0 |
| NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge | May 8, 2023 | Knowledge Distillationvalid | —Unverified | 0 |
| Algebra Error Classification with Large Language Models | May 8, 2023 | ClassificationMath | CodeCode Available | 0 |
| Non-Autoregressive Math Word Problem Solver with Unified Tree Structure | May 8, 2023 | Mathvalid | CodeCode Available | 1 |
| A nation-wide experiment, part II: the introduction of a 49-Euro-per-month travel pass in Germany -- An empirical study on this fare innovation | May 7, 2023 | valid | —Unverified | 0 |
| Faithful Question Answering with Monte-Carlo Planning | May 4, 2023 | Decision MakingQuestion Answering | CodeCode Available | 0 |
| ReMask: A Robust Information-Masking Approach for Domain Counterfactual Generation | May 4, 2023 | counterfactualDomain Adaptation | CodeCode Available | 0 |
| CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing | May 4, 2023 | Causal InferenceDisentanglement | —Unverified | 0 |
| Doubly Robust Uniform Confidence Bands for Group-Time Conditional Average Treatment Effects in Difference-in-Differences | May 3, 2023 | valid | —Unverified | 0 |
| Geometric Latent Diffusion Models for 3D Molecule Generation | May 2, 2023 | 3D Molecule GenerationUnconditional Molecule Generation | CodeCode Available | 2 |
| Large Linguistic Models: Investigating LLMs' metalinguistic abilities | May 1, 2023 | valid | —Unverified | 0 |
| How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model | Apr 30, 2023 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
| POET: A Self-learning Framework for PROFINET Industrial Operations Behaviour | Apr 29, 2023 | Anomaly DetectionIntrusion Detection | —Unverified | 0 |