{"list":"other","total":99,"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"1904.07272","title":"Introduction to Multi-Armed Bandits","created":"2019-04-15","cited_by_count":481},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333},{"id":"2306.13304","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","created":"2023-06-23","cited_by_count":274},{"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":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254},{"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":"2310.16427","title":"PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization","created":"2023-10-25","cited_by_count":233},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"2308.09662","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","created":"2023-08-18","cited_by_count":223},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207},{"id":"2303.17466","title":"Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study","created":"2023-03-30","cited_by_count":206},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199},{"id":"2211.15006","title":"Fine-tuning language models to find agreement among humans with diverse preferences","created":"2022-11-28","cited_by_count":189},{"id":"2308.13387","title":"Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs","created":"2023-08-25","cited_by_count":184},{"id":"2504.14225","title":"Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale","created":"2025-04-19","cited_by_count":178},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177},{"id":"2308.08493","title":"Time Travel in LLMs: Tracing Data Contamination in Large Language Models","created":"2023-08-16","cited_by_count":177},{"id":"2306.04181","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","created":"2023-06-07","cited_by_count":172},{"id":"2301.04246","title":"Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations","created":"2023-01-10","cited_by_count":158},{"id":"2203.13722","title":"Probing Pre-Trained Language Models for Cross-Cultural Differences in Values","created":"2022-03-25","cited_by_count":149},{"id":"2311.14096","title":"Cultural Bias and Cultural Alignment of Large Language Models","created":"2023-11-23","cited_by_count":149},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144},{"id":"2402.13231","title":"Investigating Cultural Alignment of Large Language Models","created":"2024-02-20","cited_by_count":143},{"id":"2311.09783","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","created":"2023-11-16","cited_by_count":138},{"id":"2012.15738","title":"Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences","created":"2020-12-31","cited_by_count":135},{"id":"2206.07550","title":"Evaluating and Inducing Personality in Pre-trained Language Models","created":"2022-05-20","cited_by_count":123},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122},{"id":"2402.15938","title":"Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models","created":"2024-02-24","cited_by_count":122},{"id":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97},{"id":"2204.03021","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","created":"2022-04-06","cited_by_count":93},{"id":"2307.09705","title":"CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility","created":"2023-07-19","cited_by_count":85},{"id":"2310.15337","title":"Moral Foundations of Large Language Models","created":"2023-10-23","cited_by_count":85},{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75},{"id":"2209.12106","title":"Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity","created":"2022-09-24","cited_by_count":74},{"id":"2402.09880","title":"Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence","created":"2024-02-15","cited_by_count":68},{"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":"2306.11507","title":"TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models","created":"2023-06-20","cited_by_count":58},{"id":"2312.12343","title":"LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction","created":"2023-12-19","cited_by_count":58},{"id":"2503.06072","title":"A Survey on Post-training of Large Language Models","created":"2025-03-08","cited_by_count":54},{"id":"2311.18140","title":"ROBBIE: Robust Bias Evaluation of Large Generative Language Models","created":"2023-11-29","cited_by_count":53},{"id":"2403.12958","title":"Dated Data: Tracing Knowledge Cutoffs in Large Language Models","created":"2024-03-19","cited_by_count":51},{"id":"2407.06576","title":"Virtual Personas for Language Models via an Anthology of Backstories","created":"2024-07-09","cited_by_count":51},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50},{"id":"2401.15585","title":"Evaluating Gender Bias in Large Language Models via Chain-of-Thought Prompting","created":"2024-01-28","cited_by_count":50},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45},{"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":"2401.17461","title":"Synthetic Dialogue Dataset Generation using LLM Agents","created":"2024-01-30","cited_by_count":39},{"id":"2105.02685","title":"A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations","created":"2021-05-06","cited_by_count":37},{"id":"2408.06929","title":"Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas","created":"2024-08-13","cited_by_count":37},{"id":"2112.06346","title":"ValueNet: A New Dataset for Human Value Driven Dialogue System","created":"2021-12-12","cited_by_count":34},{"id":"2205.12771","title":"Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy","created":"2022-05-25","cited_by_count":31},{"id":"2405.02501","title":"PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning","created":"2024-05-03","cited_by_count":29},{"id":"2009.13093","title":"f-Divergence Variational Inference","created":"2020-09-28","cited_by_count":28},{"id":"2301.13771","title":"The Touch\\'e23-ValueEval Dataset for Identifying Human Values behind Arguments","created":"2023-01-31","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":"2310.11053","title":"Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning","created":"2023-10-17","cited_by_count":26},{"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":"2312.15907","title":"Align on the Fly: Adapting Chatbot Behavior to Established Norms","created":"2023-12-26","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":"2407.02099","title":"Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior","created":"2024-07-02","cited_by_count":21},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20},{"id":"2406.04214","title":"ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models","created":"2024-06-06","cited_by_count":19},{"id":"2106.09069","title":"Automatic Construction of Evaluation Suites for Natural Language Generation Datasets","created":"2021-06-16","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":"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":"2411.08733","title":"Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models","created":"2024-11-13","cited_by_count":13},{"id":"2406.14783","title":"Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Framework","created":"2024-06-20","cited_by_count":11},{"id":"2310.17857","title":"From Values to Opinions: Predicting Human Behaviors and Stances Using Value-Injected Large Language Models","created":"2023-10-27","cited_by_count":10},{"id":"2402.14177","title":"Investigating Human Values in Online Communities","created":"2024-02-21","cited_by_count":10},{"id":"2501.00581","title":"Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective","created":"2024-12-31","cited_by_count":9},{"id":"2302.07371","title":"BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models","created":"2023-02-14","cited_by_count":8},{"id":"2408.01460","title":"LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models","created":"2024-07-27","cited_by_count":7},{"id":"2406.11474","title":"How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment","created":"2024-06-17","cited_by_count":6},{"id":"2504.08820","title":"CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization","created":"2025-04-09","cited_by_count":6},{"id":"2310.00378","title":"ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models","created":"2023-09-30","cited_by_count":4},{"id":"2311.06093","title":"Evaluation of Sampling Algorithms for a Pairwise Subjective Assessment Methodology","created":"2023-11-10","cited_by_count":2}],"next_cursor":null}