{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773},{"id":"2209.06899","title":"Out of One, Many: Using Language Models to Simulate Human Samples","created":"2022-09-14","cited_by_count":752},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"1610.07524","title":"Fair prediction with disparate impact: A study of bias in recidivism prediction instruments","created":"2016-10-24","cited_by_count":672},{"id":"2208.10264","title":"Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies","created":"2022-08-18","cited_by_count":515},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"2305.16367","title":"Role-Play with Large Language Models","created":"2023-05-25","cited_by_count":294},{"id":"1903.03862","title":"Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them","created":"2019-03-09","cited_by_count":268},{"id":"2411.10109","title":"LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals","created":"2024-11-15","cited_by_count":249},{"id":"2305.02547","title":"PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits","created":"2023-05-04","cited_by_count":234},{"id":"2302.02083","title":"Evaluating Large Language Models in Theory of Mind Tasks","created":"2023-02-04","cited_by_count":222},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209},{"id":"2207.07051","title":"Language models show human-like content effects on reasoning tasks","created":"2022-07-14","cited_by_count":173},{"id":"1601.03764","title":"Linear Algebraic Structure of Word Senses, with Applications to Polysemy","created":"2016-01-14","cited_by_count":165},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157},{"id":"2407.12404","title":"Analyzing the Generalization and Reliability of Steering Vectors","created":"2024-07-17","cited_by_count":143},{"id":"1812.08233","title":"Invariance, Causality and Robustness","created":"2018-12-19","cited_by_count":123},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115},{"id":"2410.21333","title":"Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse","created":"2024-10-27","cited_by_count":109},{"id":"2308.08708","title":"Consciousness in Artificial Intelligence: Insights from the Science of Consciousness","created":"2023-08-17","cited_by_count":104},{"id":"2306.07899","title":"Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks","created":"2023-06-13","cited_by_count":103},{"id":"2411.15287","title":"Sycophancy in Large Language Models: Causes and Mitigations","created":"2024-11-22","cited_by_count":101},{"id":"2401.03729","title":"The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance","created":"2024-01-08","cited_by_count":100},{"id":"2402.04049","title":"Systematic Biases in LLM Simulations of Debates","created":"2024-02-06","cited_by_count":99},{"id":"2310.11501","title":"CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations","created":"2023-10-17","cited_by_count":97},{"id":"2311.02462","title":"Levels of AGI for Operationalizing Progress on the Path to AGI","created":"2023-11-04","cited_by_count":96},{"id":"2305.13735","title":"Aligning Large Language Models through Synthetic Feedback","created":"2023-05-23","cited_by_count":75},{"id":"2306.07951","title":"Questioning the Survey Responses of Large Language Models","created":"2023-06-13","cited_by_count":74},{"id":"2410.24190","title":"Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters","created":"2024-10-31","cited_by_count":71},{"id":"2502.00873","title":"Language Models Use Trigonometry to Do Addition","created":"2025-02-02","cited_by_count":70},{"id":"2306.03917","title":"Turning large language models into cognitive models","created":"2023-06-06","cited_by_count":67},{"id":"2502.16761","title":"Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions","created":"2025-02-24","cited_by_count":66},{"id":"2405.18870","title":"LLMs achieve adult human performance on higher-order theory of mind tasks","created":"2024-05-29","cited_by_count":61},{"id":"2411.05403","title":"Benchmarking Distributional Alignment of Large Language Models","created":"2024-11-08","cited_by_count":61},{"id":"2312.15524","title":"The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspective","created":"2023-12-24","cited_by_count":59},{"id":"2411.04427","title":"One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity","created":"2024-11-07","cited_by_count":58},{"id":"2304.11085","title":"Testing the Reliability of ChatGPT for Text Annotation and Classification: A Cautionary Remark","created":"2023-04-17","cited_by_count":54},{"id":"2407.06576","title":"Virtual Personas for Language Models via an Anthology of Backstories","created":"2024-07-09","cited_by_count":51},{"id":"2305.09620","title":"AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction","created":"2023-05-16","cited_by_count":48},{"id":"2401.02843","title":"Thousands of AI Authors on the Future of AI","created":"2024-01-05","cited_by_count":48},{"id":"2408.02784","title":"LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theory","created":"2024-08-05","cited_by_count":47},{"id":"2402.05699","title":"Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation","created":"2024-02-08","cited_by_count":46},{"id":"2302.07267","title":"Diminished Diversity-of-Thought in a Standard Large Language Model","created":"2023-02-13","cited_by_count":45},{"id":"2503.05336","title":"Toward an Evaluation Science for Generative AI Systems","created":"2025-03-07","cited_by_count":45},{"id":"2402.12649","title":"Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation","created":"2024-02-20","cited_by_count":41},{"id":"2305.15041","title":"Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science","created":"2023-05-24","cited_by_count":37},{"id":"2410.20268","title":"Centaur: a foundation model of human cognition","created":"2024-10-26","cited_by_count":36},{"id":"2401.08572","title":"The illusion of artificial inclusion","created":"2024-01-16","cited_by_count":34},{"id":"2503.02080","title":"Linear Representations of Political Perspective Emerge in Large Language Models","created":"2025-03-03","cited_by_count":32},{"id":"2405.07248","title":"Limited Ability of LLMs to Simulate Human Psychological Behaviours: a Psychometric Analysis","created":"2024-05-12","cited_by_count":31},{"id":"2501.08579","title":"LLM-based Human Simulations Have Not Yet Been Reliable","created":"2025-01-15","cited_by_count":30},{"id":"2410.19599","title":"Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina","created":"2024-10-25","cited_by_count":29},{"id":"2402.07282","title":"How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?","created":"2024-02-11","cited_by_count":27},{"id":"2501.05171","title":"Emergence of polarization in networks of large language model agents","created":"2025-01-09","cited_by_count":26},{"id":"2406.01382","title":"Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function","created":"2024-06-03","cited_by_count":24},{"id":"2406.03198","title":"The Impossibility of Fair LLMs","created":"2024-05-28","cited_by_count":22},{"id":"2308.00189","title":"Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?","created":"2023-07-31","cited_by_count":19},{"id":"2407.08867","title":"Perceptions of Sentient AI and Other Digital Minds: Evidence from the AI, Morality, and Sentience (AIMS) Survey","created":"2024-07-11","cited_by_count":15},{"id":"2412.02802","title":"Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model","created":"2024-12-03","cited_by_count":15},{"id":"2102.04215","title":"The Moral Consideration of Artificial Entities: A Literature Review","created":"2021-01-26","cited_by_count":10},{"id":"2311.11081","title":"Can AI Serve as a Substitute for Human Subjects in Software Engineering Research?","created":"2023-11-18","cited_by_count":8},{"id":"2501.06834","title":"LLMs Model Non-WEIRD Populations: Experiments with Synthetic Cultural Agents","created":"2025-01-12","cited_by_count":6},{"id":"2410.15442","title":"Exploring Social Desirability Response Bias in Large Language Models: Evidence from GPT-4 Simulations","created":"2024-10-20","cited_by_count":5},{"id":"2409.17990","title":"Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models","created":"2024-09-26","cited_by_count":4},{"id":"2412.07788","title":"Human Behavior Simulation: Objectives, Methodologies, and Open Problems","created":"2024-11-26","cited_by_count":1},{"id":"2501.15351","title":"Fairness in LLM-Generated Surveys","created":"2025-01-25","cited_by_count":1}],"next_cursor":null}