{"list":"other","total":73,"rows":[{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"2312.01552","title":"The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning","created":"2023-12-04","cited_by_count":257},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"1705.07120","title":"VAE with a VampPrior","created":"2017-05-19","cited_by_count":248},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215},{"id":"2412.03304","title":"Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation","created":"2024-12-04","cited_by_count":191},{"id":"2406.09948","title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","created":"2024-06-14","cited_by_count":173},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167},{"id":"2402.16786","title":"Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models","created":"2024-02-26","cited_by_count":162},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153},{"id":"2311.14096","title":"Cultural Bias and Cultural Alignment of Large Language Models","created":"2023-11-23","cited_by_count":149},{"id":"2402.13231","title":"Investigating Cultural Alignment of Large Language Models","created":"2024-02-20","cited_by_count":143},{"id":"2506.20920","title":"FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language","created":"2025-06-26","cited_by_count":143},{"id":"2303.07895","title":"The Learnability of In-Context Learning","created":"2023-03-14","cited_by_count":127},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122},{"id":"2209.14338","title":"Who is GPT-3? An Exploration of Personality, Values and Demographics","created":"2022-09-28","cited_by_count":112},{"id":"2309.12342","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","created":"2023-08-25","cited_by_count":112},{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103},{"id":"2404.15238","title":"CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies","created":"2024-04-23","cited_by_count":98},{"id":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97},{"id":"2310.15337","title":"Moral Foundations of Large Language Models","created":"2023-10-23","cited_by_count":85},{"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":"2306.03082","title":"InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models","created":"2023-06-05","cited_by_count":68},{"id":"2002.03293","title":"On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm","created":"2020-02-09","cited_by_count":61},{"id":"2404.16308","title":"WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models","created":"2024-04-25","cited_by_count":60},{"id":"2410.02683","title":"DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life","created":"2024-10-03","cited_by_count":59},{"id":"1910.12958","title":"Sinkhorn Divergences for Unbalanced Optimal Transport","created":"2019-10-28","cited_by_count":55},{"id":"2504.15236","title":"Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions","created":"2025-04-21","cited_by_count":52},{"id":"2405.04655","title":"Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense","created":"2024-05-07","cited_by_count":51},{"id":"2501.15463","title":"Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?","created":"2025-01-26","cited_by_count":51},{"id":"2402.10946","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","created":"2024-02-09","cited_by_count":50},{"id":"2406.04428","title":"MoralBench: Moral Evaluation of LLMs","created":"2024-06-06","cited_by_count":50},{"id":"2405.14125","title":"ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation","created":"2024-05-23","cited_by_count":47},{"id":"2305.14889","title":"Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory","created":"2023-05-24","cited_by_count":43},{"id":"2310.12481","title":"Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models","created":"2023-10-19","cited_by_count":43},{"id":"2502.16534","title":"Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs","created":"2025-02-23","cited_by_count":39},{"id":"2503.10694","title":"Medical Large Language Model Benchmarks Should Prioritize Construct Validity","created":"2025-03-12","cited_by_count":38},{"id":"2402.01349","title":"LLMs May Perform MCQA by Selecting the Least Incorrect Option","created":"2024-02-02","cited_by_count":33},{"id":"2504.08863","title":"An Evaluation of Cultural Value Alignment in LLM","created":"2025-04-11","cited_by_count":28},{"id":"2411.06032","title":"LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output","created":"2024-11-09","cited_by_count":27},{"id":"2502.08045","title":"Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs","created":"2025-02-12","cited_by_count":26},{"id":"2406.11565","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","created":"2024-06-17","cited_by_count":24},{"id":"2311.16421","title":"CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models","created":"2023-11-28","cited_by_count":23},{"id":"2407.10725","title":"CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses","created":"2024-07-15","cited_by_count":23},{"id":"2412.00207","title":"Can LLM \"Self-report\"?: Evaluating the Validity of Self-report Scales in Measuring Personality Design in LLM-based Chatbots","created":"2024-11-29","cited_by_count":20},{"id":"2106.09069","title":"Automatic Construction of Evaluation Suites for Natural Language Generation Datasets","created":"2021-06-16","cited_by_count":18},{"id":"2310.06458","title":"Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features","created":"2023-10-10","cited_by_count":18},{"id":"2409.10566","title":"Eureka: Evaluating and Understanding Large Foundation Models","created":"2024-09-13","cited_by_count":18},{"id":"2505.01015","title":"Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items","created":"2025-05-02","cited_by_count":18},{"id":"2406.14230","title":"Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing","created":"2024-06-20","cited_by_count":17},{"id":"2511.03980","title":"LLMs and Cultural Values: the Impact of Prompt Language and Explicit Cultural Framing","created":"2025-11-06","cited_by_count":17},{"id":"2405.13974","title":"CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models","created":"2024-05-22","cited_by_count":16},{"id":"2406.14504","title":"Translating Across Cultures: LLMs for Intralingual Cultural Adaptation","created":"2024-06-20","cited_by_count":16},{"id":"2409.12106","title":"Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models","created":"2024-09-18","cited_by_count":13},{"id":"2509.01418","title":"On the Alignment of Large Language Models with Global Human Opinion","created":"2025-09-01","cited_by_count":13},{"id":"2404.10857","title":"D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation","created":"2024-04-16","cited_by_count":11},{"id":"2407.16891","title":"Cultural Value Differences of LLMs: Prompt, Language, and Model Size","created":"2024-06-17","cited_by_count":10},{"id":"2507.13490","title":"Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?","created":"2025-07-17","cited_by_count":8},{"id":"2007.01488","title":"On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation","created":"2020-07-03","cited_by_count":7},{"id":"2504.12911","title":"Benchmarking Multi-National Value Alignment for Large Language Models","created":"2025-04-17","cited_by_count":7},{"id":"2209.07518","title":"Distribution Aware Metrics for Conditional Natural Language Generation","created":"2022-09-15","cited_by_count":6},{"id":"2306.04116","title":"Unbalanced Optimal Transport for Unbalanced Word Alignment","created":"2023-06-07","cited_by_count":6},{"id":"2505.09595","title":"WorldView-Bench: A Benchmark for Evaluating Global Cultural Perspectives in Large Language Models","created":"2025-05-14","cited_by_count":5},{"id":"2508.16013","title":"Political Ideology Shifts in Large Language Models","created":"2025-08-22","cited_by_count":5},{"id":"2507.21831","title":"Introducing HALC: A general pipeline for the systematic and reliable construction of prompts for automated coding with LLMs in the computational social sciences","created":"2025-07-29","cited_by_count":2},{"id":"2512.21809","title":"On The Conceptualization and Societal Impact of Cross-Cultural Bias","created":"2025-12-26","cited_by_count":1}],"next_cursor":null}