{"total":67,"rows":[{"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":"2305.14763","title":"Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models","created":"2023-05-24","cited_by_count":163,"area":"lr"},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151,"area":null},{"id":"2311.13614","title":"HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data","created":"2023-11-22","cited_by_count":126,"area":"mllm"},{"id":"2212.08037","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","created":"2022-12-15","cited_by_count":112,"area":null},{"id":"2305.06984","title":"Evaluating Open-Domain Question Answering in the Era of Large Language Models","created":"2023-05-11","cited_by_count":111,"area":null},{"id":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107,"area":"rag"},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2303.07274","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","created":"2023-03-13","cited_by_count":80,"area":null},{"id":"2404.10981","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","created":"2024-04-17","cited_by_count":77,"area":"rag"},{"id":"2501.02189","title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges","created":"2025-01-04","cited_by_count":47,"area":"mllm"},{"id":"2402.11756","title":"MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs","created":"2024-02-19","cited_by_count":46,"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":"2507.02856","title":"Answer Matching Outperforms Multiple Choice for Language Model Evaluation","created":"2025-07-03","cited_by_count":41,"area":null},{"id":"2503.13509","title":"MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance","created":"2025-03-13","cited_by_count":39,"area":null},{"id":"2310.02567","title":"Improving Automatic VQA Evaluation Using Large Language Models","created":"2023-10-04","cited_by_count":37,"area":null},{"id":"2404.16032","title":"Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents","created":"2024-04-24","cited_by_count":27,"area":"rag"},{"id":"2402.07270","title":"Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy","created":"2024-02-11","cited_by_count":26,"area":"mllm"},{"id":"2406.04291","title":"Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2405.13622","title":"Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation","created":"2024-05-22","cited_by_count":25,"area":"rag"},{"id":"2412.09582","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","created":"2024-12-12","cited_by_count":25,"area":null},{"id":"2305.14332","title":"Evaluating and Modeling Attribution for Cross-Lingual Question Answering","created":"2023-05-23","cited_by_count":21,"area":null},{"id":"2411.16863","title":"Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering","created":"2024-11-25","cited_by_count":20,"area":"mllm"},{"id":"2411.15041","title":"mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA","created":"2024-11-22","cited_by_count":19,"area":"mllm"},{"id":"2311.08106","title":"Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models","created":"2023-11-14","cited_by_count":18,"area":null},{"id":"2401.05736","title":"Cross-modal Retrieval for Knowledge-based Visual Question Answering","created":"2024-01-11","cited_by_count":13,"area":null},{"id":"2406.19593","title":"SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs","created":"2024-06-28","cited_by_count":12,"area":"mllm"},{"id":"2211.05007","title":"Discord Questions: A Computational Approach To Diversity Analysis in News Coverage","created":"2022-11-09","cited_by_count":11,"area":null},{"id":"2503.17073","title":"A Study into Investigating Temporal Robustness of LLMs","created":"2025-03-21","cited_by_count":11,"area":null},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2511.00330","title":"Sherlock: Reliable and Efficient Agentic Workflow Execution","created":"2025-11-01","cited_by_count":11,"area":"lr"},{"id":"2308.00002","title":"An Overview Of Temporal Commonsense Reasoning and Acquisition","created":"2023-07-28","cited_by_count":10,"area":"lr"},{"id":"2405.06034","title":"Bayesian Prediction-Powered Inference","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2305.19585","title":"LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interaction","created":"2023-05-31","cited_by_count":7,"area":null},{"id":"2401.12078","title":"Temporal Blind Spots in Large Language Models","created":"2024-01-22","cited_by_count":7,"area":null},{"id":"2404.05465","title":"HAMMR: HierArchical MultiModal React agents for generic VQA","created":"2024-04-08","cited_by_count":7,"area":"agents"},{"id":"2511.22715","title":"ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering","created":"2025-11-27","cited_by_count":7,"area":"lr"},{"id":"2404.04728","title":"Navigating the Landscape of Hint Generation Research: From the Past to the Future","created":"2024-04-06","cited_by_count":6,"area":null},{"id":"2502.16358","title":"Wrong Answers Can Also Be Useful: PlausibleQA -- A Large-Scale QA Dataset with Answer Plausibility Scores","created":"2025-02-22","cited_by_count":5,"area":null},{"id":"2507.12441","title":"Describe Anything Model for Visual Question Answering on Text-rich Images","created":"2025-07-16","cited_by_count":5,"area":"mllm"},{"id":"2310.06641","title":"How (not) to ensemble LVLMs for VQA","created":"2023-10-10","cited_by_count":4,"area":"mllm"},{"id":"2412.01626","title":"WikiHint: A Human-Annotated Dataset for Hint Ranking and Generation","created":"2024-12-02","cited_by_count":4,"area":null},{"id":"2502.19409","title":"ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models","created":"2025-02-26","cited_by_count":4,"area":"lr"},{"id":"2506.13743","title":"LTRR: Learning To Rank Retrievers for LLMs","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2511.07659","title":"Revisiting NLI: Towards Cost-Effective and Human-Aligned Metrics for Evaluating LLMs in Question Answering","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2512.23959","title":"HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling","created":"2025-12-30","cited_by_count":4,"area":"rag"},{"id":"2303.00242","title":"DIFFQG: Generating Questions to Summarize Factual Changes","created":"2023-03-01","cited_by_count":3,"area":null},{"id":"2305.15344","title":"Learning Answer Generation using Supervision from Automatic Question Answering Evaluators","created":"2023-05-24","cited_by_count":3,"area":"rag"},{"id":"2509.08897","title":"Recurrence Meets Transformers for Universal Multimodal Retrieval","created":"2025-09-10","cited_by_count":3,"area":"mllm"},{"id":"2602.17445","title":"ABCD: All Biases Come Disguised","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2306.05036","title":"Mapping the Challenges of HCI: An Application and Evaluation of ChatGPT for Mining Insights at Scale","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2510.13103","title":"ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2511.22843","title":"Breaking the Visual Shortcuts in Multimodal Knowledge-Based Visual Question Answering","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2512.09066","title":"ORCA: Open-ended Response Correctness Assessment for Audio Question Answering","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2512.22633","title":"Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair","created":"2025-12-27","cited_by_count":2,"area":"lr"},{"id":"2604.07146","title":"Learning to Search: A Decision-Based Agent for Knowledge-Based Visual Question Answering","created":"2026-04-08","cited_by_count":2,"area":"mllm"},{"id":"2206.12664","title":"Evaluation of Semantic Answer Similarity Metrics","created":"2022-06-25","cited_by_count":1,"area":null},{"id":"2309.12250","title":"SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2511.17432","title":"SMILE: A Composite Lexical-Semantic Metric for Question-Answering Evaluation","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2602.15915","title":"MaS-VQA: A Mask-and-Select Framework for Knowledge-Based Visual Question Answering","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2602.06050","title":"Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering","created":"2026-01-14","cited_by_count":0,"area":"mllm"},{"id":"2605.04638","title":"Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Models","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.23937","title":"When Retrieval Metrics Mislead: Measuring Policy Signal in Long-Horizon Tool-Use Agents","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.07383","title":"MMAgent-R$^2$: Learning to Rerank and Reject for Agentic mRAG","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"id":"2609.15180","title":"Rethinking Correctness for Uncertainty Estimation in Clinical Prediction with Vision-Language Models","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.19879","title":"V\\={a}kQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.02736","title":"TPBench: A Turning-Point Benchmark for Dialogue Compression","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}