{"total":84,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2306.14050","title":"Symbolic Chain-of-Thought Distillation: Small Models Can Also \"Think\" Step-by-Step","created":"2023-06-24","cited_by_count":148,"area":"lr"},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2306.04387","title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","created":"2023-06-07","cited_by_count":126,"area":null},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125,"area":null},{"id":"2210.06726","title":"Explanations from Large Language Models Make Small Reasoners Better","created":"2022-10-13","cited_by_count":124,"area":"lr"},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97,"area":null},{"id":"2111.08284","title":"Few-Shot Self-Rationalization with Natural Language Prompts","created":"2021-11-16","cited_by_count":83,"area":null},{"id":"2205.12404","title":"FLUTE: Figurative Language Understanding through Textual Explanations","created":"2022-05-24","cited_by_count":79,"area":null},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2203.05081","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","created":"2022-03-09","cited_by_count":60,"area":null},{"id":"2310.15166","title":"Large Language Models are Visual Reasoning Coordinators","created":"2023-10-23","cited_by_count":58,"area":"lr"},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2204.03359","title":"ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO","created":"2022-04-07","cited_by_count":37,"area":null},{"id":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"area":null},{"id":"2410.20482","title":"What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration","created":"2024-10-27","cited_by_count":31,"area":"lr"},{"id":"2310.00647","title":"Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning","created":"2023-10-01","cited_by_count":30,"area":"mllm"},{"id":"2401.06654","title":"Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks","created":"2024-01-12","cited_by_count":28,"area":null},{"id":"2207.04343","title":"Explaining Chest X-ray Pathologies in Natural Language","created":"2022-07-09","cited_by_count":27,"area":null},{"id":"2112.04873","title":"Nice perfume. How long did you marinate in it? Multimodal Sarcasm Explanation","created":"2021-12-09","cited_by_count":25,"area":null},{"id":"2106.13876","title":"Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations","created":"2021-06-25","cited_by_count":24,"area":null},{"id":"2211.08129","title":"Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works","created":"2022-11-15","cited_by_count":24,"area":null},{"id":"2210.13513","title":"ExPUNations: Augmenting Puns with Keywords and Explanations","created":"2022-10-24","cited_by_count":21,"area":null},{"id":"2405.01474","title":"Understanding Figurative Meaning through Explainable Visual Entailment","created":"2024-05-02","cited_by_count":19,"area":"mllm"},{"id":"2403.17368","title":"ChatGPT Rates Natural Language Explanation Quality Like Humans: But on Which Scales?","created":"2024-03-26","cited_by_count":17,"area":null},{"id":"2112.06204","title":"Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup","created":"2021-12-12","cited_by_count":16,"area":null},{"id":"2204.02380","title":"CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations","created":"2022-04-05","cited_by_count":16,"area":"lr"},{"id":"2206.11083","title":"Investigating the Benefits of Free-Form Rationales","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2308.09033","title":"Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks","created":"2023-08-17","cited_by_count":12,"area":null},{"id":"2310.19145","title":"Learning to Follow Object-Centric Image Editing Instructions Faithfully","created":"2023-10-29","cited_by_count":12,"area":"diffusion"},{"id":"2410.13016","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","created":"2024-10-16","cited_by_count":12,"area":null},{"id":"2205.12469","title":"Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI","created":"2022-05-25","cited_by_count":11,"area":null},{"id":"2410.04749","title":"LLaVA Needs More Knowledge: Retrieval Augmented Natural Language Generation with Knowledge Graph for Explaining Thoracic Pathologies","created":"2024-10-07","cited_by_count":11,"area":"rag"},{"id":"2309.01617","title":"DeViL: Decoding Vision features into Language","created":"2023-09-04","cited_by_count":10,"area":null},{"id":"2309.02155","title":"S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning","created":"2023-09-05","cited_by_count":10,"area":null},{"id":"2408.11965","title":"CT-AGRG: Automated Abnormality-Guided Report Generation from 3D Chest CT Volumes","created":"2024-08-21","cited_by_count":10,"area":null},{"id":"2504.13275","title":"ChartQA-X: Generating Explanations for Visual Chart Reasoning","created":"2025-04-17","cited_by_count":10,"area":null},{"id":"2311.05085","title":"Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2207.11401","title":"Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations","created":"2022-07-23","cited_by_count":8,"area":"mllm"},{"id":"2305.07355","title":"ZARA: Improving Few-Shot Self-Rationalization for Small Language Models","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2311.02018","title":"Active Reasoning in an Open-World Environment","created":"2023-11-03","cited_by_count":8,"area":null},{"id":"2207.09625","title":"Explicit Image Caption Editing","created":"2022-07-20","cited_by_count":7,"area":null},{"id":"2310.14670","title":"Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2209.06103","title":"VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models","created":"2022-09-12","cited_by_count":6,"area":"mllm"},{"id":"2212.04231","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","created":"2022-12-08","cited_by_count":6,"area":null},{"id":"2406.19170","title":"The Illusion of Competence: Evaluating the Effect of Explanations on Users' Mental Models of Visual Question Answering Systems","created":"2024-06-27","cited_by_count":6,"area":null},{"id":"2112.05197","title":"Self-Supervised Bot Play for Conversational Recommendation with Justifications","created":"2021-12-09","cited_by_count":5,"area":null},{"id":"2312.13594","title":"Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2410.12284","title":"Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2502.06600","title":"Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2203.15704","title":"Fine-Grained Visual Entailment","created":"2022-03-29","cited_by_count":4,"area":"lr"},{"id":"2306.02980","title":"KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations","created":"2023-06-05","cited_by_count":4,"area":null},{"id":"2310.14418","title":"REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2311.12391","title":"From Wrong To Right: A Recursive Approach Towards Vision-Language Explanation","created":"2023-11-21","cited_by_count":4,"area":"lr"},{"id":"2402.13587","title":"A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation","created":"2024-02-21","cited_by_count":4,"area":null},{"id":"2403.04343","title":"Adaptive Task Balancing for Visual Instruction Tuning via Inter-Task Contribution and Intra-Task Difficulty","created":"2024-03-07","cited_by_count":4,"area":"mllm"},{"id":"2510.14741","title":"DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models","created":"2025-10-16","cited_by_count":4,"area":"lr"},{"id":"2301.10799","title":"Towards a Unified Model for Generating Answers and Explanations in Visual Question Answering","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2311.05043","title":"Zero-shot Translation of Attention Patterns in VQA Models to Natural Language","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2205.11686","title":"On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization","created":"2022-05-24","cited_by_count":2,"area":null},{"id":"2208.09266","title":"Diverse Video Captioning by Adaptive Spatio-temporal Attention","created":"2022-08-19","cited_by_count":2,"area":null},{"id":"2305.13235","title":"SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2311.07556","title":"Using Natural Language Explanations to Improve Robustness of In-context Learning","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2409.14785","title":"Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models","created":"2024-09-23","cited_by_count":2,"area":"mllm"},{"id":"2210.07126","title":"Challenges in Explanation Quality Evaluation","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2310.00503","title":"Black-box Attacks on Image Activity Prediction and its Natural Language Explanations","created":"2023-09-30","cited_by_count":1,"area":null},{"id":"2311.10933","title":"Representing visual classification as a linear combination of words","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2406.19054","title":"A look under the hood of the Interactive Deep Learning Enterprise (No-IDLE)","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2410.08469","title":"Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP","created":"2024-10-11","cited_by_count":1,"area":"mllm"},{"id":"2501.08514","title":"Multimodal Fake News Video Explanation: Dataset, Analysis and Evaluation","created":"2025-01-15","cited_by_count":1,"area":null},{"id":"2502.00711","title":"VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework","created":"2025-02-02","cited_by_count":1,"area":"lr"},{"id":"2508.12430","title":"Adversarial Attacks on VQA-NLE: Exposing and Alleviating Inconsistencies in Visual Question Answering Explanations","created":"2025-08-17","cited_by_count":1,"area":null},{"id":"2508.14280","title":"Multi-Rationale Explainable Object Recognition via Contrastive Conditional Inference","created":"2025-08-19","cited_by_count":1,"area":"mllm"},{"id":"2512.06814","title":"CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2303.04388","title":"Interpretable Visual Question Answering Referring to Outside Knowledge","created":"2023-03-08","cited_by_count":0,"area":null},{"id":"2303.05983","title":"Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creation","created":"2023-03-10","cited_by_count":0,"area":null},{"id":"2408.17006","title":"Retrieval-Augmented Natural Language Reasoning for Explainable Visual Question Answering","created":"2024-08-30","cited_by_count":0,"area":"lr"},{"id":"2508.04427","title":"Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2603.18752","title":"WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2607.03882","title":"Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2609.29496","title":"Evaluating Explanation-Driven Vision-Language Reasoning via Generation Order Interventions","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.33713","title":"BIRD: Distilling Decision Boundaries into Rationales for MLLM Adaptation","created":"2026-09-27","cited_by_count":0,"area":"mllm"}],"next_cursor":null}