{"list":"other","total":51,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"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":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2106.15772","title":"A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers","created":"2021-06-30","cited_by_count":318},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243},{"id":"1805.01052","title":"Constituency Parsing with a Self-Attentive Encoder","created":"2018-05-02","cited_by_count":199},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":159},{"id":"1812.11760","title":"Multilingual Constituency Parsing with Self-Attention and Pre-Training","created":"2018-12-31","cited_by_count":117},{"id":"1905.00270","title":"ASER: A Large-scale Eventuality Knowledge Graph","created":"2019-05-01","cited_by_count":89},{"id":"1908.07245","title":"GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge","created":"2019-08-20","cited_by_count":79},{"id":"2310.14491","title":"Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models","created":"2023-10-23","cited_by_count":50},{"id":"2305.11383","title":"Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning","created":"2023-05-19","cited_by_count":49},{"id":"2401.17464","title":"Efficient Tool Use with Chain-of-Abstraction Reasoning","created":"2024-01-30","cited_by_count":33},{"id":"2104.02137","title":"ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities","created":"2021-04-05","cited_by_count":28},{"id":"2401.13478","title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval","created":"2024-01-24","cited_by_count":23},{"id":"2305.05191","title":"COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective","created":"2023-05-09","cited_by_count":22},{"id":"1907.12048","title":"Probabilistic Models of Relational Implication","created":"2019-07-28","cited_by_count":17},{"id":"2206.01532","title":"Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization","created":"2022-06-03","cited_by_count":17},{"id":"2311.09174","title":"AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph","created":"2023-11-15","cited_by_count":17},{"id":"2311.13133","title":"LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms","created":"2023-11-22","cited_by_count":14},{"id":"2001.04170","title":"Joint Reasoning for Multi-Faceted Commonsense Knowledge","created":"2020-01-13","cited_by_count":12},{"id":"2204.03286","title":"Entailment Graph Learning with Textual Entailment and Soft Transitivity","created":"2022-04-07","cited_by_count":11},{"id":"2104.07846","title":"Multivalent Entailment Graphs for Question Answering","created":"2021-04-16","cited_by_count":10},{"id":"2210.06694","title":"SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller","created":"2022-10-13","cited_by_count":10},{"id":"2208.00318","title":"Smoothing Entailment Graphs with Language Models","created":"2022-07-30","cited_by_count":8},{"id":"2109.09412","title":"Incorporating Temporal Information in Entailment Graph Mining","created":"2021-09-20","cited_by_count":7},{"id":"2210.07621","title":"Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths","created":"2022-10-14","cited_by_count":6},{"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},{"id":"2310.19651","title":"Dynamics of Instruction Fine-Tuning for Chinese Large Language Models","created":"2023-10-30","cited_by_count":6},{"id":"2401.14003","title":"ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases","created":"2024-01-25","cited_by_count":6},{"id":"1811.06203","title":"Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference","created":"2018-11-15","cited_by_count":5},{"id":"2310.18804","title":"Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting","created":"2023-10-28","cited_by_count":5}],"next_cursor":null}