{"total":54,"rows":[{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194,"area":null},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2205.12700","title":"BITE: Textual Backdoor Attacks with Iterative Trigger Injection","created":"2022-05-25","cited_by_count":53,"area":"safety"},{"id":"2205.02318","title":"Language Models in the Loop: Incorporating Prompting into Weak Supervision","created":"2022-05-04","cited_by_count":52,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2204.07447","title":"Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters","created":"2022-04-15","cited_by_count":44,"area":null},{"id":"2410.22770","title":"InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models","created":"2024-10-30","cited_by_count":42,"area":"safety"},{"id":"2501.05435","title":"Neuro-Symbolic AI in 2024: A Systematic Review","created":"2025-01-09","cited_by_count":38,"area":null},{"id":"2212.10534","title":"DISCO: Distilling Counterfactuals with Large Language Models","created":"2022-12-20","cited_by_count":30,"area":null},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2210.04873","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2305.11596","title":"Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation","created":"2023-05-19","cited_by_count":21,"area":null},{"id":"2210.04992","title":"Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction","created":"2022-10-10","cited_by_count":15,"area":null},{"id":"2404.17475","title":"CEval: A Benchmark for Evaluating Counterfactual Text Generation","created":"2024-04-26","cited_by_count":15,"area":null},{"id":"2212.10784","title":"Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?","created":"2022-12-21","cited_by_count":13,"area":null},{"id":"2310.16738","title":"Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentation","created":"2023-10-25","cited_by_count":11,"area":null},{"id":"2212.00921","title":"AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization","created":"2022-12-02","cited_by_count":10,"area":null},{"id":"2212.05421","title":"Feature-Level Debiased Natural Language Understanding","created":"2022-12-11","cited_by_count":10,"area":null},{"id":"2210.13575","title":"Does Self-Rationalization Improve Robustness to Spurious Correlations?","created":"2022-10-24","cited_by_count":9,"area":null},{"id":"2305.18623","title":"Alfred: A System for Prompted Weak Supervision","created":"2023-05-29","cited_by_count":8,"area":null},{"id":"2406.04286","title":"ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2208.11464","title":"FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition","created":"2022-08-24","cited_by_count":7,"area":null},{"id":"2403.00435","title":"Hierarchical Indexing for Retrieval-Augmented Opinion Summarization","created":"2024-03-01","cited_by_count":7,"area":"rag"},{"id":"2403.00462","title":"LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues","created":"2024-03-01","cited_by_count":7,"area":null},{"id":"2211.16202","title":"AutoCAD: Automatically Generating Counterfactuals for Mitigating Shortcut Learning","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2305.17041","title":"RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2401.09615","title":"Learning Shortcuts: On the Misleading Promise of NLU in Language Models","created":"2024-01-17","cited_by_count":4,"area":null},{"id":"2410.11660","title":"Eliciting Textual Descriptions from Representations of Continuous Prompts","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2211.03862","title":"Looking at the Overlooked: An Analysis on the Word-Overlap Bias in Natural Language Inference","created":"2022-11-07","cited_by_count":3,"area":null},{"id":"2212.08399","title":"Assessing the Impact of Sequence Length Learning on Classification Tasks for Transformer Encoder Models","created":"2022-12-16","cited_by_count":3,"area":null},{"id":"2306.02190","title":"Stubborn Lexical Bias in Data and Models","created":"2023-06-03","cited_by_count":3,"area":null},{"id":"2310.11191","title":"Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2409.19541","title":"Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2504.16188","title":"FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2302.14413","title":"SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2305.12123","title":"Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2311.00292","title":"IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2403.05788","title":"On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarization","created":"2024-03-09","cited_by_count":2,"area":null},{"id":"2504.01450","title":"CASCADE Your Datasets for Cross-Mode Knowledge Retrieval of Language Models","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2507.05527","title":"Mitigating Shortcut Learning with InterpoLated Learning","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2303.02846","title":"Contrastive variational information bottleneck for aspect-based sentiment analysis","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2402.01867","title":"Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2410.20710","title":"Relation-based Counterfactual Data Augmentation and Contrastive Learning for Robustifying Natural Language Inference Models","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2502.04797","title":"Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2504.18376","title":"Evaluating the Scalability and Adversarial Generalization of GRPO-Trained NLI Models","created":"2025-04-25","cited_by_count":1,"area":"lr"},{"id":"2506.14587","title":"SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2211.02971","title":"Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference","created":"2022-11-05","cited_by_count":0,"area":null},{"id":"2406.12060","title":"Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding","created":"2024-06-17","cited_by_count":0,"area":"moe"},{"id":"2606.03284","title":"SEA-NLI: Natural Language Inference as a Lens into Southeast Asian Cultural Understanding","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2608.09209","title":"UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}