{"total":88,"rows":[{"id":"2307.02477","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","created":"2023-07-05","cited_by_count":246,"area":"lr"},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"area":null},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207,"area":null},{"id":"2210.06774","title":"Re3: Generating Longer Stories With Recursive Reprompting and Revision","created":"2022-10-13","cited_by_count":193,"area":null},{"id":"2202.11705","title":"COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics","created":"2022-02-23","cited_by_count":161,"area":null},{"id":"2306.05836","title":"Can Large Language Models Infer Causation from Correlation?","created":"2023-06-09","cited_by_count":146,"area":null},{"id":"2312.04350","title":"CLadder: Assessing Causal Reasoning in Language Models","created":"2023-12-07","cited_by_count":107,"area":"lr"},{"id":"2109.06835","title":"The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation","created":"2021-09-14","cited_by_count":97,"area":null},{"id":"2402.17644","title":"Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data","created":"2024-02-27","cited_by_count":63,"area":"lr"},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2106.04571","title":"TIMEDIAL: Temporal Commonsense Reasoning in Dialog","created":"2021-06-08","cited_by_count":55,"area":null},{"id":"2310.15910","title":"Characterizing Mechanisms for Factual Recall in Language Models","created":"2023-10-24","cited_by_count":48,"area":null},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45,"area":null},{"id":"2203.02225","title":"ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification","created":"2022-03-04","cited_by_count":45,"area":null},{"id":"2108.00648","title":"From LSAT: The Progress and Challenges of Complex Reasoning","created":"2021-08-02","cited_by_count":43,"area":null},{"id":"2203.13926","title":"CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues","created":"2022-03-25","cited_by_count":38,"area":null},{"id":"2301.08571","title":"Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences","created":"2023-01-20","cited_by_count":31,"area":null},{"id":"2203.14040","title":"Visual Abductive Reasoning","created":"2022-03-26","cited_by_count":30,"area":"lr"},{"id":"2205.12630","title":"Multimodal Knowledge Alignment with Reinforcement Learning","created":"2022-05-25","cited_by_count":30,"area":null},{"id":"2212.10534","title":"DISCO: Distilling Counterfactuals with Large Language Models","created":"2022-12-20","cited_by_count":30,"area":null},{"id":"2402.11597","title":"Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?","created":"2024-02-18","cited_by_count":30,"area":null},{"id":"2305.16572","title":"Counterfactual reasoning: Testing language models' understanding of hypothetical scenarios","created":"2023-05-26","cited_by_count":27,"area":"lr"},{"id":"2104.06511","title":"\"I'm Not Mad\": Commonsense Implications of Negation and Contradiction","created":"2021-04-13","cited_by_count":26,"area":null},{"id":"2305.14010","title":"IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions","created":"2023-05-23","cited_by_count":26,"area":null},{"id":"2402.18139","title":"Cause and Effect: Can Large Language Models Truly Understand Causality?","created":"2024-02-28","cited_by_count":23,"area":null},{"id":"2305.05191","title":"COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective","created":"2023-05-09","cited_by_count":22,"area":"lr"},{"id":"2407.03993","title":"A Survey on Natural Language Counterfactual Generation","created":"2024-07-04","cited_by_count":21,"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":"2206.05395","title":"Why is constrained neural language generation particularly challenging?","created":"2022-06-11","cited_by_count":19,"area":null},{"id":"2110.11589","title":"Text Counterfactuals via Latent Optimization and Shapley-Guided Search","created":"2021-10-22","cited_by_count":16,"area":null},{"id":"2409.17027","title":"Counterfactual Token Generation in Large Language Models","created":"2024-09-25","cited_by_count":14,"area":null},{"id":"2410.16676","title":"CausalEval: Towards Better Causal Reasoning in Language Models","created":"2024-10-22","cited_by_count":13,"area":"lr"},{"id":"2407.01992","title":"Is Your Large Language Model Knowledgeable or a Choices-Only Cheater?","created":"2024-07-02","cited_by_count":12,"area":null},{"id":"2109.07713","title":"Transferable Persona-Grounded Dialogues via Grounded Minimal Edits","created":"2021-09-16","cited_by_count":10,"area":null},{"id":"2208.12848","title":"Coalescing Global and Local Information for Procedural Text Understanding","created":"2022-08-26","cited_by_count":10,"area":null},{"id":"2104.00929","title":"Sketch and Customize: A Counterfactual Story Generator","created":"2021-04-02","cited_by_count":9,"area":null},{"id":"2109.04053","title":"Table-based Fact Verification with Salience-aware Learning","created":"2021-09-09","cited_by_count":9,"area":null},{"id":"2109.08544","title":"Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules","created":"2021-09-17","cited_by_count":9,"area":null},{"id":"2112.05417","title":"Unsupervised Editing for Counterfactual Stories","created":"2021-12-10","cited_by_count":8,"area":null},{"id":"2311.01620","title":"ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2210.16838","title":"Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues","created":"2022-10-30","cited_by_count":7,"area":null},{"id":"2212.10754","title":"CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding","created":"2022-12-21","cited_by_count":7,"area":null},{"id":"2310.08796","title":"End-to-end Story Plot Generator","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2311.17438","title":"CLOMO: Counterfactual Logical Modification with Large Language Models","created":"2023-11-29","cited_by_count":7,"area":"lr"},{"id":"2305.15268","title":"EvEval: A Comprehensive Evaluation of Event Semantics for Large Language Models","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2310.03293","title":"A New Dialogue Response Generation Agent for Large Language Models by Asking Questions to Detect User's Intentions","created":"2023-10-05","cited_by_count":6,"area":"agents"},{"id":"2311.07424","title":"Hallucination Augmented Recitations for Language Models","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2409.13733","title":"RNR: Teaching Large Language Models to Follow Roles and Rules","created":"2024-09-10","cited_by_count":6,"area":null},{"id":"2505.13770","title":"Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2208.00329","title":"PASTA: A Dataset for Modeling Participant States in Narratives","created":"2022-07-31","cited_by_count":5,"area":null},{"id":"2210.11431","title":"Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2305.08152","title":"STORYWARS: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation","created":"2023-05-14","cited_by_count":5,"area":null},{"id":"2406.19307","title":"The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning","created":"2024-06-27","cited_by_count":5,"area":null},{"id":"2602.15851","title":"Narrative Theory-Driven LLM Methods for Automatic Story Generation and Understanding: A Survey","created":"2026-01-23","cited_by_count":5,"area":null},{"id":"2310.20072","title":"Automatic Evaluation of Generative Models with Instruction Tuning","created":"2023-10-30","cited_by_count":4,"area":null},{"id":"2404.17513","title":"A Comprehensive Evaluation on Event Reasoning of Large Language Models","created":"2024-04-26","cited_by_count":4,"area":"lr"},{"id":"2506.05188","title":"Counterfactual reasoning: an analysis of in-context emergence","created":"2025-06-05","cited_by_count":4,"area":"lr"},{"id":"2605.26029","title":"CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists","created":"2026-05-25","cited_by_count":4,"area":"agents"},{"id":"2104.00814","title":"CURIE: An Iterative Querying Approach for Reasoning About Situations","created":"2021-04-01","cited_by_count":3,"area":null},{"id":"2106.03973","title":"Generating Hypothetical Events for Abductive Inference","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2209.07760","title":"Possible Stories: Evaluating Situated Commonsense Reasoning under Multiple Possible Scenarios","created":"2022-09-16","cited_by_count":3,"area":"lr"},{"id":"2212.03747","title":"Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2503.16401","title":"Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them","created":"2025-03-20","cited_by_count":3,"area":"lr"},{"id":"2103.04941","title":"InFillmore: Frame-Guided Language Generation with Bidirectional Context","created":"2021-03-08","cited_by_count":2,"area":null},{"id":"2106.08914","title":"$C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2202.13151","title":"COMPASS: a Creative Support System that Alerts Novelists to the Unnoticed Missing Contents","created":"2022-02-26","cited_by_count":2,"area":null},{"id":"2210.07493","title":"Psychology-guided Controllable Story Generation","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2312.11720","title":"Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Models","created":"2023-12-18","cited_by_count":2,"area":"lr"},{"id":"2404.11978","title":"EVIT: Event-Oriented Instruction Tuning for Event Reasoning","created":"2024-04-18","cited_by_count":2,"area":"lr"},{"id":"2408.05793","title":"SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Events","created":"2024-08-11","cited_by_count":2,"area":null},{"id":"2202.09049","title":"CLSEG: Contrastive Learning of Story Ending Generation","created":"2022-02-18","cited_by_count":1,"area":null},{"id":"2212.03278","title":"Counterfactual reasoning: Do language models need world knowledge for causal understanding?","created":"2022-12-06","cited_by_count":1,"area":"lr"},{"id":"2403.06936","title":"Counterfactual Reasoning with Knowledge Graph Embeddings","created":"2024-03-11","cited_by_count":1,"area":null},{"id":"2406.02804","title":"ACCORD: Closing the Commonsense Measurability Gap","created":"2024-06-04","cited_by_count":1,"area":"lr"},{"id":"2505.19430","title":"Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2511.06418","title":"How Well Do LLMs Understand Drug Mechanisms? A Knowledge + Reasoning Evaluation Dataset","created":"2025-11-09","cited_by_count":1,"area":"lr"},{"id":"2207.05155","title":"Can Language Models perform Abductive Commonsense Reasoning?","created":"2022-07-07","cited_by_count":0,"area":"lr"},{"id":"2308.02103","title":"Prompt2Gaussia: Uncertain Prompt-learning for Script Event Prediction","created":"2023-08-04","cited_by_count":0,"area":null},{"id":"2502.12354","title":"Human-centered explanation does not fit all: The interplay of sociotechnical, cognitive, and individual factors in the effect AI explanations in algorithmic decision-making","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2509.23698","title":"VIVA+: Human-Centered Situational Decision-Making","created":"2025-09-28","cited_by_count":0,"area":"mllm"},{"id":"2601.17226","title":"Retell, Reward, Repeat: Reinforcement Learning for Narrative Theory-Informed Story Retelling","created":"2026-01-23","cited_by_count":0,"area":"alignment"},{"id":"2605.24885","title":"DTO: a Differentiable Training Objective for Effective Counterfactual Story Rewriting","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2608.28264","title":"Finding Where the Buck Stops: An Automated Failure Attribution-Based Reflection Framework for Multi-Agent Collaboration","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2608.30716","title":"SocialReasonBench: A Video-QA Benchmark for Social Reasoning with Counterfactual Narrative Videos","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.14677","title":"The Garden of Forking Prompts: How Users Explore Narrative Space in Story Generation","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.22409","title":"Contextual Causality with Large Language Models: A Survey","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.38406","title":"Evaluating Whether LLMs Can Reliably Connect the DOTs?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.13057","title":"CoBe: A Benchmark For Conversational Counterfactual Text Editing","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}