{"list":"other","total":78,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2311.07397","title":"AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation","created":"2023-11-13","cited_by_count":300},{"id":"2305.16739","title":"AlignScore: Evaluating Factual Consistency with a Unified Alignment Function","created":"2023-05-26","cited_by_count":288},{"id":"2311.16839","title":"Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","created":"2023-11-28","cited_by_count":225},{"id":"2310.05492","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","created":"2023-10-09","cited_by_count":223},{"id":"2305.10790","title":"Listen, Think, and Understand","created":"2023-05-18","cited_by_count":209},{"id":"2307.15266","title":"RSGPT: A Remote Sensing Vision Language Model and Benchmark","created":"2023-07-28","cited_by_count":207},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183},{"id":"2310.01469","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","created":"2023-10-02","cited_by_count":177},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172},{"id":"2306.06687","title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","created":"2023-06-11","cited_by_count":169},{"id":"2308.10168","title":"Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?","created":"2023-08-20","cited_by_count":168},{"id":"2204.07931","title":"On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?","created":"2022-04-17","cited_by_count":138},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135},{"id":"2306.16092","title":"Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture","created":"2023-06-28","cited_by_count":122},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86},{"id":"2307.16372","title":"LP-MusicCaps: LLM-Based Pseudo Music Captioning","created":"2023-07-31","cited_by_count":83},{"id":"2312.11865","title":"Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach","created":"2023-12-19","cited_by_count":79},{"id":"2312.01701","title":"Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites","created":"2023-12-04","cited_by_count":61},{"id":"2308.16890","title":"TouchStone: Evaluating Vision-Language Models by Language Models","created":"2023-08-31","cited_by_count":55},{"id":"2304.14406","title":"Putting People in Their Place: Affordance-Aware Human Insertion into Scenes","created":"2023-04-27","cited_by_count":53},{"id":"2305.11426","title":"Post Hoc Explanations of Language Models Can Improve Language Models","created":"2023-05-19","cited_by_count":50},{"id":"2102.10618","title":"Towards the Unification and Robustness of Perturbation and Gradient Based Explanations","created":"2021-02-21","cited_by_count":47},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45},{"id":"2312.05200","title":"DelucionQA: Detecting Hallucinations in Domain-specific Question Answering","created":"2023-12-08","cited_by_count":43},{"id":"2310.18344","title":"Chainpoll: A high efficacy method for LLM hallucination detection","created":"2023-10-22","cited_by_count":39},{"id":"2309.03118","title":"Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphs","created":"2023-09-06","cited_by_count":35},{"id":"2312.10763","title":"M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts","created":"2023-12-17","cited_by_count":32},{"id":"2107.11970","title":"Boosting Entity-aware Image Captioning with Multi-modal Knowledge Graph","created":"2021-07-26","cited_by_count":31},{"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},{"id":"2305.12256","title":"Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination","created":"2023-05-20","cited_by_count":27},{"id":"2203.15625","title":"PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision","created":"2022-03-29","cited_by_count":25},{"id":"2304.00387","title":"HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions","created":"2023-04-01","cited_by_count":25},{"id":"2312.02219","title":"Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models","created":"2023-12-03","cited_by_count":23},{"id":"2312.14069","title":"EmphAssess : a Prosodic Benchmark on Assessing Emphasis Transfer in Speech-to-Speech Models","created":"2023-12-21","cited_by_count":22},{"id":"2303.02961","title":"Models See Hallucinations: Evaluating the Factuality in Video Captioning","created":"2023-03-06","cited_by_count":19},{"id":"2311.02847","title":"Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs","created":"2023-11-06","cited_by_count":19},{"id":"2212.05765","title":"Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue","created":"2022-12-12","cited_by_count":18},{"id":"2307.12168","title":"Hallucination Improves the Performance of Unsupervised Visual Representation Learning","created":"2023-07-22","cited_by_count":16},{"id":"2103.12258","title":"Hallucination of speech recognition errors with sequence to sequence learning","created":"2021-03-23","cited_by_count":14},{"id":"2311.04177","title":"Enhancing LLM Intelligence with ARM-RAG: Auxiliary Rationale Memory for Retrieval Augmented Generation","created":"2023-11-07","cited_by_count":14},{"id":"2311.17851","title":"Leveraging VLM-Based Pipelines to Annotate 3D Objects","created":"2023-11-29","cited_by_count":10},{"id":"2312.14206","title":"LLM4VG: Large Language Models Evaluation for Video Grounding","created":"2023-12-21","cited_by_count":8},{"id":"2307.16139","title":"User-Controlled Knowledge Fusion in Large Language Models: Balancing Creativity and Hallucination","created":"2023-07-30","cited_by_count":7},{"id":"2108.08836","title":"Multi-Object Tracking with Hallucinated and Unlabeled Videos","created":"2021-08-19","cited_by_count":6},{"id":"2303.08081","title":"Explanation Shift: How Did the Distribution Shift Impact the Model?","created":"2023-03-14","cited_by_count":6},{"id":"2010.08034","title":"Overfitting or Underfitting? Understand Robustness Drop in Adversarial Training","created":"2020-10-15","cited_by_count":5},{"id":"2309.03340","title":"Parameter Efficient Audio Captioning With Faithful Guidance Using Audio-text Shared Latent Representation","created":"2023-09-06","cited_by_count":5},{"id":"2312.17343","title":"AQUALLM: Audio Question Answering Data Generation Using Large Language Models","created":"2023-12-28","cited_by_count":4},{"id":"2302.14204","title":"HalluAudio: Hallucinating Frequency as Concepts for Few-Shot Audio Classification","created":"2023-02-27","cited_by_count":2},{"id":"2201.00693","title":"Multimodal Entity Tagging with Multimodal Knowledge Base","created":"2021-12-21","cited_by_count":1}],"next_cursor":null}