{"total":63,"rows":[{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743,"area":null},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729,"area":"alignment"},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208,"area":null},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169,"area":"lr"},{"id":"2308.11730","title":"Knowledge Graph Prompting for Multi-Document Question Answering","created":"2023-08-22","cited_by_count":152,"area":null},{"id":"2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","created":"2023-05-02","cited_by_count":128,"area":null},{"id":"2206.01347","title":"MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data","created":"2022-06-03","cited_by_count":121,"area":null},{"id":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101,"area":null},{"id":"2409.10102","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","created":"2024-09-16","cited_by_count":83,"area":"rag"},{"id":"2208.00748","title":"Efficient Long-Text Understanding with Short-Text Models","created":"2022-08-01","cited_by_count":71,"area":null},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2507.21206","title":"Agentic Web: Weaving the Next Web with AI Agents","created":"2025-07-28","cited_by_count":45,"area":"agents"},{"id":"2110.07803","title":"Attacking Open-domain Question Answering by Injecting Misinformation","created":"2021-10-15","cited_by_count":41,"area":null},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2406.13397","title":"MoreHopQA: More Than Multi-hop Reasoning","created":"2024-06-19","cited_by_count":37,"area":"lr"},{"id":"2310.09754","title":"EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification","created":"2023-10-15","cited_by_count":36,"area":null},{"id":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32,"area":null},{"id":"2406.06580","title":"Break the Chain: Large Language Models Can be Shortcut Reasoners","created":"2024-06-04","cited_by_count":32,"area":"lr"},{"id":"2204.10496","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","created":"2022-04-22","cited_by_count":23,"area":null},{"id":"2103.03872","title":"Rissanen Data Analysis: Examining Dataset Characteristics via Description Length","created":"2021-03-05","cited_by_count":22,"area":null},{"id":"2104.04515","title":"Connecting Attributions and QA Model Behavior on Realistic Counterfactuals","created":"2021-04-09","cited_by_count":20,"area":null},{"id":"2310.00322","title":"Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games","created":"2023-09-30","cited_by_count":17,"area":"agents"},{"id":"2501.17144","title":"FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data","created":"2025-01-28","cited_by_count":14,"area":null},{"id":"2107.03242","title":"Robustifying Multi-hop QA through Pseudo-Evidentiality Training","created":"2021-07-07","cited_by_count":13,"area":null},{"id":"2107.11823","title":"Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy","created":"2021-07-25","cited_by_count":13,"area":null},{"id":"2205.11729","title":"From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2409.05197","title":"Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?","created":"2024-09-08","cited_by_count":10,"area":"lr"},{"id":"2211.16220","title":"Which Shortcut Solution Do Question Answering Models Prefer to Learn?","created":"2022-11-29","cited_by_count":9,"area":null},{"id":"2305.14901","title":"Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2504.19674","title":"SAGE: A Generic Framework for LLM Safety Evaluation","created":"2025-04-28","cited_by_count":8,"area":"safety"},{"id":"2205.12496","title":"Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts","created":"2022-05-25","cited_by_count":7,"area":"lr"},{"id":"2210.04234","title":"Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answering","created":"2022-10-09","cited_by_count":7,"area":"lr"},{"id":"2210.07138","title":"Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning","created":"2022-10-13","cited_by_count":7,"area":"lr"},{"id":"2308.13768","title":"Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content","created":"2023-08-26","cited_by_count":7,"area":"safety"},{"id":"2101.05988","title":"Coarse-grained decomposition and fine-grained interaction for multi-hop question answering","created":"2021-01-15","cited_by_count":5,"area":null},{"id":"2212.10381","title":"To Adapt or to Annotate: Challenges and Interventions for Domain Adaptation in Open-Domain Question Answering","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2302.10291","title":"Can Large Language Models Change User Preference Adversarially?","created":"2023-01-05","cited_by_count":5,"area":"safety"},{"id":"2307.00335","title":"Single Sequence Prediction over Reasoning Graphs for Multi-hop QA","created":"2023-07-01","cited_by_count":5,"area":"lr"},{"id":"2310.18359","title":"DeSIQ: Towards an Unbiased, Challenging Benchmark for Social Intelligence Understanding","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2502.18273","title":"Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2112.09658","title":"Reasoning Chain Based Adversarial Attack for Multi-hop Question Answering","created":"2021-12-17","cited_by_count":4,"area":null},{"id":"2209.01824","title":"A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension","created":"2022-09-05","cited_by_count":4,"area":null},{"id":"2111.09029","title":"Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction","created":"2021-11-17","cited_by_count":3,"area":null},{"id":"2205.14851","title":"Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2209.06923","title":"Prompt-based Conservation Learning for Multi-hop Question Answering","created":"2022-09-14","cited_by_count":3,"area":null},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2509.21035","title":"CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineering","created":"2025-09-25","cited_by_count":3,"area":"agents"},{"id":"2104.08744","title":"Generative Context Pair Selection for Multi-hop Question Answering","created":"2021-04-18","cited_by_count":2,"area":null},{"id":"2203.09073","title":"Ask to Understand: Question Generation for Multi-hop Question Answering","created":"2022-03-17","cited_by_count":2,"area":null},{"id":"2302.05963","title":"Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering","created":"2023-02-12","cited_by_count":2,"area":"lr"},{"id":"2410.05289","title":"MARS: A neurosymbolic approach for interpretable drug discovery","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2502.16523","title":"Pay Attention to Real World Perturbations! Natural Robustness Evaluation in Machine Reading Comprehension","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2210.05208","title":"How Well Do Multi-hop Reading Comprehension Models Understand Date Information?","created":"2022-10-11","cited_by_count":1,"area":"lr"},{"id":"2602.04853","title":"Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say \"I Don't Know\"","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2605.10862","title":"RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems","created":"2026-05-11","cited_by_count":1,"area":"rag"},{"id":"2403.14197","title":"Context Quality Matters in Training Fusion-in-Decoder for Extractive Open-Domain Question Answering","created":"2024-03-21","cited_by_count":0,"area":"rag"},{"id":"2505.04844","title":"Osiris: A Lightweight Open-Source Hallucination Detection System","created":"2025-05-07","cited_by_count":0,"area":"rag"},{"id":"2510.22689","title":"Rule-Based Explanations for Retrieval-Augmented LLM Systems","created":"2025-10-26","cited_by_count":0,"area":"rag"},{"id":"2512.12688","title":"How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2607.20459","title":"THOR: A Theta-Gamma Hierarchical Oscillatory Reasoning Framework for Multi-hop QA","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2609.33565","title":"Dr. Free: You Don't Need Difficulty Rewards for Self-Evolving Search Agents","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36984","title":"REALHOP: Rethinking Multi-Hop Reasoning Evaluation via Behavioral Auditing","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}