{"list":"other","total":102,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1602.01585","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","created":"2016-02-04","cited_by_count":520},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"1703.00955","title":"Toward Controlled Generation of Text","created":"2017-03-02","cited_by_count":272},{"id":"1806.00064","title":"Efficient Low-rank Multimodal Fusion with Modality-Specific Factors","created":"2018-05-31","cited_by_count":270},{"id":"1705.09655","title":"Style Transfer from Non-Parallel Text by Cross-Alignment","created":"2017-05-26","cited_by_count":248},{"id":"1803.11138","title":"Colorless green recurrent networks dream hierarchically","created":"2018-03-29","cited_by_count":213},{"id":"1803.06535","title":"Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer","created":"2018-03-17","cited_by_count":211},{"id":"1804.06437","title":"Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer","created":"2018-04-17","cited_by_count":191},{"id":"1804.00891","title":"Hyperspherical Variational Auto-Encoders","created":"2018-04-03","cited_by_count":189},{"id":"2011.00416","title":"Deep Learning for Text Style Transfer: A Survey","created":"2020-11-01","cited_by_count":162},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152},{"id":"1711.06861","title":"Style Transfer in Text: Exploration and Evaluation","created":"2017-11-18","cited_by_count":146},{"id":"1808.04339","title":"Disentangled Representation Learning for Non-Parallel Text Style Transfer","created":"2018-08-13","cited_by_count":127},{"id":"1804.09000","title":"Style Transfer Through Back-Translation","created":"2018-04-24","cited_by_count":124},{"id":"1901.05534","title":"Lagging Inference Networks and Posterior Collapse in Variational Autoencoders","created":"2019-01-16","cited_by_count":124},{"id":"2004.04092","title":"Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space","created":"2020-04-05","cited_by_count":114},{"id":"1703.10931","title":"Sentence Simplification with Deep Reinforcement Learning","created":"2017-03-31","cited_by_count":109},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108},{"id":"2307.06908","title":"Generating Benchmarks for Factuality Evaluation of Language Models","created":"2023-07-13","cited_by_count":105},{"id":"1802.05312","title":"Learning Deep Disentangled Embeddings with the F-Statistic Loss","created":"2018-02-14","cited_by_count":101},{"id":"2305.16130","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","created":"2023-05-25","cited_by_count":98},{"id":"2005.04322","title":"LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation","created":"2020-05-09","cited_by_count":93},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91},{"id":"1702.08139","title":"Improved Variational Autoencoders for Text Modeling using Dilated Convolutions","created":"2017-02-27","cited_by_count":81},{"id":"1808.10805","title":"Spherical Latent Spaces for Stable Variational Autoencoders","created":"2018-08-31","cited_by_count":67},{"id":"2505.24832","title":"How much do language models memorize?","created":"2025-05-30","cited_by_count":61},{"id":"1802.03052","title":"WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-Hop Inference","created":"2018-02-08","cited_by_count":60},{"id":"2109.06379","title":"Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation","created":"2021-09-14","cited_by_count":60},{"id":"1907.05789","title":"Generating Sentences from Disentangled Syntactic and Semantic Spaces","created":"2019-07-06","cited_by_count":59},{"id":"2305.01579","title":"Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise","created":"2023-05-02","cited_by_count":54},{"id":"1612.00394","title":"Definition Modeling: Learning to define word embeddings in natural language","created":"2016-12-01","cited_by_count":46},{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46},{"id":"2101.10579","title":"Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs","created":"2021-01-26","cited_by_count":45},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45},{"id":"1904.01173","title":"A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations","created":"2019-04-02","cited_by_count":37},{"id":"2505.19488","title":"Understanding Transformer from the Perspective of Associative Memory","created":"2025-05-26","cited_by_count":34},{"id":"2010.00389","title":"A Survey on Explainability in Machine Reading Comprehension","created":"2020-10-01","cited_by_count":33},{"id":"2210.02889","title":"A Distributional Lens for Multi-Aspect Controllable Text Generation","created":"2022-10-06","cited_by_count":33},{"id":"2409.05283","title":"On the Relationship between Truth and Political Bias in Language Models","created":"2024-09-09","cited_by_count":31},{"id":"2208.00638","title":"Composable Text Controls in Latent Space with ODEs","created":"2022-08-01","cited_by_count":28},{"id":"1911.03882","title":"Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders","created":"2019-11-10","cited_by_count":27},{"id":"2212.08307","title":"Controllable Text Generation via Probability Density Estimation in the Latent Space","created":"2022-12-16","cited_by_count":27},{"id":"1908.11527","title":"Implicit Deep Latent Variable Models for Text Generation","created":"2019-08-30","cited_by_count":26},{"id":"2010.02983","title":"Plug and Play Autoencoders for Conditional Text Generation","created":"2020-10-06","cited_by_count":26},{"id":"2104.05115","title":"Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models","created":"2021-04-11","cited_by_count":22},{"id":"2105.15053","title":"Factorising Meaning and Form for Intent-Preserving Paraphrasing","created":"2021-05-31","cited_by_count":22},{"id":"2203.03463","title":"Hierarchical Sketch Induction for Paraphrase Generation","created":"2022-03-07","cited_by_count":22},{"id":"1905.12304","title":"Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning","created":"2019-05-29","cited_by_count":21},{"id":"2207.06130","title":"Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation","created":"2022-07-13","cited_by_count":20},{"id":"1905.12752","title":"Unsupervised Paraphrasing without Translation","created":"2019-05-29","cited_by_count":19},{"id":"1906.02181","title":"Syntax-Infused Variational Autoencoder for Text Generation","created":"2019-06-05","cited_by_count":19},{"id":"2109.07169","title":"Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders","created":"2021-09-15","cited_by_count":19},{"id":"2010.00735","title":"Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer","created":"2020-10-02","cited_by_count":18},{"id":"2505.12189","title":"Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering","created":"2025-05-18","cited_by_count":18},{"id":"2504.16929","title":"I-Con: A Unifying Framework for Representation Learning","created":"2025-04-23","cited_by_count":16},{"id":"2305.12563","title":"A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers","created":"2023-05-21","cited_by_count":15},{"id":"2501.13042","title":"Does Table Source Matter? Benchmarking and Improving Multimodal Scientific Table Understanding and Reasoning","created":"2025-01-22","cited_by_count":15},{"id":"2209.15217","title":"Hyperbolic VAE via Latent Gaussian Distributions","created":"2022-09-30","cited_by_count":14},{"id":"1905.06512","title":"Incorporating Sememes into Chinese Definition Modeling","created":"2019-05-16","cited_by_count":13},{"id":"2204.00511","title":"Learning Disentangled Representations of Negation and Uncertainty","created":"2022-04-01","cited_by_count":13},{"id":"2210.02898","title":"Learning Disentangled Representations for Natural Language Definitions","created":"2022-09-22","cited_by_count":12},{"id":"2205.05862","title":"AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling","created":"2022-05-12","cited_by_count":10},{"id":"2311.08579","title":"Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders","created":"2023-11-14","cited_by_count":6},{"id":"2402.00723","title":"Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders","created":"2024-02-01","cited_by_count":6},{"id":"2206.11184","title":"Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles","created":"2022-06-22","cited_by_count":5},{"id":"2210.06230","title":"Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder","created":"2022-10-12","cited_by_count":5},{"id":"2312.11532","title":"Topic-VQ-VAE: Leveraging Latent Codebooks for Flexible Topic-Guided Document Generation","created":"2023-12-15","cited_by_count":5},{"id":"2112.03154","title":"VAE based Text Style Transfer with Pivot Words Enhancement Learning","created":"2021-12-06","cited_by_count":4},{"id":"2207.03777","title":"Hidden Schema Networks","created":"2022-07-08","cited_by_count":4},{"id":"2403.04400","title":"Exploring Continual Learning of Compositional Generalization in NLI","created":"2024-03-07","cited_by_count":4},{"id":"2102.00769","title":"GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer","created":"2021-02-01","cited_by_count":3},{"id":"2205.05943","title":"Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs","created":"2022-05-12","cited_by_count":3},{"id":"2312.13208","title":"LlaMaVAE: Guiding Large Language Model Generation via Continuous Latent Sentence Spaces","created":"2023-12-20","cited_by_count":3},{"id":"2410.05077","title":"ZEBRA: Zero-Shot Example-Based Retrieval Augmentation for Commonsense Question Answering","created":"2024-10-07","cited_by_count":3},{"id":"2505.00004","title":"LangVAE and LangSpace: Building and Probing for Language Model VAEs","created":"2025-03-29","cited_by_count":3},{"id":"2312.00277","title":"Text Attribute Control via Closed-Loop Disentanglement","created":"2023-12-01","cited_by_count":2}],"next_cursor":"100"}