{"list":"other","total":52,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"2211.00053","title":"Generating Sequences by Learning to Self-Correct","created":"2022-10-31","cited_by_count":277},{"id":"2311.17311","title":"Universal Self-Consistency for Large Language Model Generation","created":"2023-11-29","cited_by_count":203},{"id":"1606.05433","title":"FVQA: Fact-based Visual Question Answering","created":"2016-06-17","cited_by_count":181},{"id":"2402.00367","title":"Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration","created":"2024-02-01","cited_by_count":180},{"id":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167},{"id":"2311.03287","title":"Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges","created":"2023-11-06","cited_by_count":131},{"id":"1607.05910","title":"Visual Question Answering: A Survey of Methods and Datasets","created":"2016-07-20","cited_by_count":123},{"id":"2305.18201","title":"A Critical Evaluation of Evaluations for Long-form Question Answering","created":"2023-05-29","cited_by_count":111},{"id":"2102.05169","title":"Decontextualization: Making Sentences Stand-Alone","created":"2021-02-09","cited_by_count":102},{"id":"2308.15126","title":"Evaluation and Analysis of Hallucination in Large Vision-Language Models","created":"2023-08-29","cited_by_count":99},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89},{"id":"2303.11315","title":"Context-faithful Prompting for Large Language Models","created":"2023-03-20","cited_by_count":80},{"id":"1907.10568","title":"Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References","created":"2019-07-24","cited_by_count":48},{"id":"2310.02567","title":"Improving Automatic VQA Evaluation Using Large Language Models","created":"2023-10-04","cited_by_count":37},{"id":"2402.06544","title":"Calibrating Long-form Generations from Large Language Models","created":"2024-02-09","cited_by_count":32},{"id":"2010.12852","title":"Beyond VQA: Generating Multi-word Answer and Rationale to Visual Questions","created":"2020-10-24","cited_by_count":19},{"id":"2203.11048","title":"How Do We Answer Complex Questions: Discourse Structure of Long-form Answers","created":"2022-03-21","cited_by_count":19},{"id":"2302.14117","title":"AVscript: Accessible Video Editing with Audio-Visual Scripts","created":"2023-02-27","cited_by_count":19},{"id":"2205.10646","title":"Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics","created":"2022-05-21","cited_by_count":18},{"id":"2307.07589","title":"GenAssist: Making Image Generation Accessible","created":"2023-07-14","cited_by_count":18},{"id":"1909.03396","title":"Quality Estimation for Image Captions Based on Large-scale Human Evaluations","created":"2019-09-08","cited_by_count":17},{"id":"2010.03160","title":"Vision Skills Needed to Answer Visual Questions","created":"2020-10-07","cited_by_count":17},{"id":"2308.11662","title":"VQA Therapy: Exploring Answer Differences by Visually Grounding Answers","created":"2023-08-21","cited_by_count":14},{"id":"2311.03754","title":"Which is better? Exploring Prompting Strategy For LLM-based Metrics","created":"2023-11-07","cited_by_count":14},{"id":"2402.10382","title":"Making Short-Form Videos Accessible with Hierarchical Video Summaries","created":"2024-02-16","cited_by_count":14},{"id":"2311.15562","title":"Fully Authentic Visual Question Answering Dataset from Online Communities","created":"2023-11-27","cited_by_count":9},{"id":"2307.15745","title":"Context-VQA: Towards Context-Aware and Purposeful Visual Question Answering","created":"2023-07-28","cited_by_count":6},{"id":"2011.04883","title":"Determining Question-Answer Plausibility in Crowdsourced Datasets Using Multi-Task Learning","created":"2020-11-10","cited_by_count":5},{"id":"2305.14779","title":"Alt-Text with Context: Improving Accessibility for Images on Twitter","created":"2023-05-24","cited_by_count":3},{"id":"2307.08773","title":"\"Customization is Key\": Reconfigurable Content Tokens for Accessible Data Visualizations","created":"2023-07-17","cited_by_count":2}],"next_cursor":null}