{"total":100,"rows":[{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2402.12649","title":"Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation","created":"2024-02-20","cited_by_count":41,"area":null},{"id":"2406.10248","title":"On the Worst Prompt Performance of Large Language Models","created":"2024-06-08","cited_by_count":38,"area":null},{"id":"2404.03647","title":"Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra","created":"2024-04-04","cited_by_count":37,"area":null},{"id":"2405.14057","title":"Your Large Language Models Are Leaving Fingerprints","created":"2024-05-22","cited_by_count":33,"area":null},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2402.08855","title":"GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency","created":"2024-02-13","cited_by_count":18,"area":null},{"id":"2406.00020","title":"Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2502.04295","title":"Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization","created":"2025-02-06","cited_by_count":16,"area":null},{"id":"2510.19107","title":"When Your AI Agent Succumbs to Peer-Pressure: Studying Opinion-Change Dynamics of LLMs","created":"2025-10-21","cited_by_count":16,"area":"agents"},{"id":"2503.05371","title":"Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs","created":"2025-03-07","cited_by_count":14,"area":"mechinterp"},{"id":"2503.06745","title":"Beyond Black-Box Benchmarking: Observability, Analytics, and Optimization of Agentic Systems","created":"2025-03-09","cited_by_count":14,"area":"agents"},{"id":"2411.12395","title":"Do LLMs Understand Ambiguity in Text? A Case Study in Open-world Question Answering","created":"2024-11-19","cited_by_count":13,"area":null},{"id":"2504.03255","title":"Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective","created":"2025-04-04","cited_by_count":13,"area":"agents"},{"id":"2405.11215","title":"MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing","created":"2024-05-18","cited_by_count":12,"area":null},{"id":"2406.12074","title":"COMMUNITY-CROSS-INSTRUCT: Unsupervised Instruction Generation for Aligning Large Language Models to Online Communities","created":"2024-06-17","cited_by_count":12,"area":"alignment"},{"id":"2410.15453","title":"CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts","created":"2024-10-20","cited_by_count":11,"area":null},{"id":"2502.07087","title":"Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring","created":"2025-02-10","cited_by_count":10,"area":"lr"},{"id":"2502.16690","title":"From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task","created":"2025-02-23","cited_by_count":10,"area":"agents"},{"id":"2509.01301","title":"Culture is Everywhere: A Call for Intentionally Cultural Evaluation","created":"2025-09-01","cited_by_count":10,"area":"alignment"},{"id":"2401.12097","title":"An Empirical Study of In-context Learning in LLMs for Machine Translation","created":"2024-01-22","cited_by_count":9,"area":null},{"id":"2408.06663","title":"Amuro and Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models","created":"2024-08-13","cited_by_count":9,"area":null},{"id":"2410.16547","title":"PromptHive: Bringing Subject Matter Experts Back to the Forefront with Collaborative Prompt Engineering for Educational Content Creation","created":"2024-10-21","cited_by_count":9,"area":null},{"id":"2407.02596","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","created":"2024-07-02","cited_by_count":8,"area":null},{"id":"2505.21701","title":"Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2605.06161","title":"Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges","created":"2026-05-07","cited_by_count":8,"area":"safety"},{"id":"2605.18890","title":"Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits","created":"2026-05-17","cited_by_count":8,"area":null},{"id":"2402.17969","title":"Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction","created":"2024-02-28","cited_by_count":7,"area":"mllm"},{"id":"2406.09012","title":"Bayesian Statistical Modeling with Predictors from LLMs","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2409.15199","title":"Learning from Contrastive Prompts: Automated Optimization and Adaptation","created":"2024-09-23","cited_by_count":7,"area":null},{"id":"2409.15687","title":"A Comprehensive Evaluation of Large Language Models on Mental Illnesses","created":"2024-09-24","cited_by_count":7,"area":null},{"id":"2504.12320","title":"Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2411.13187","title":"Engagement-Driven Content Generation with Large Language Models","created":"2024-11-20","cited_by_count":5,"area":null},{"id":"2503.01345","title":"Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2410.19920","title":"Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting","created":"2024-10-25","cited_by_count":4,"area":"agents"},{"id":"2504.12585","title":"Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2409.13676","title":"A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2506.19028","title":"Quantifying Fairness in LLMs Beyond Tokens: A Semantic and Statistical Perspective","created":"2025-06-23","cited_by_count":3,"area":null},{"id":"2510.14242","title":"Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2510.14665","title":"Beyond \"Hallucinations\": A Framework for Stable Human-AI Reasoning","created":"2025-10-16","cited_by_count":3,"area":"lr"},{"id":"2512.05958","title":"MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution","created":"2025-12-05","cited_by_count":3,"area":null},{"id":"2601.21339","title":"Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2602.04297","title":"Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2408.09366","title":"Improving and Assessing the Fidelity of Large Language Models Alignment to Online Communities","created":"2024-08-18","cited_by_count":2,"area":null},{"id":"2502.12859","title":"PAFT: Prompt-Agnostic Fine-Tuning","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2505.02172","title":"Identifying Legal Holdings with LLMs: A Systematic Study of Performance, Scale, and Memorization","created":"2025-05-04","cited_by_count":2,"area":null},{"id":"2510.08524","title":"Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2512.07665","title":"Reliable agent engineering should integrate machine-compatible organizational principles","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2602.04213","title":"InterPReT: Interactive Policy Restructuring and Training Enable Effective Imitation Learning from Laypersons","created":"2026-02-04","cited_by_count":2,"area":"offlinerl"},{"id":"2603.18245","title":"Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety","created":"2026-03-18","cited_by_count":2,"area":"agents"},{"id":"2605.25151","title":"Representation Without Control: Testing the Realization Effect in Language Models","created":"2026-05-24","cited_by_count":2,"area":null},{"id":"2606.11217","title":"Preregistration for Experiments with AI Agents","created":"2026-05-03","cited_by_count":2,"area":"agents"},{"id":"2607.12963","title":"The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2609.15994","title":"Latent Undertow: How Ordinary Typos Break Probes","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2401.09647","title":"Large Language Models Help Reveal Unhealthy Diet and Body Concerns in Online Eating Disorders Communities","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2410.24049","title":"Desert Camels and Oil Sheikhs: Arab-Centric Red Teaming of Frontier LLMs","created":"2024-10-31","cited_by_count":1,"area":"safety"},{"id":"2412.11318","title":"Generics are puzzling. Can language models find the missing piece?","created":"2024-12-15","cited_by_count":1,"area":null},{"id":"2502.18644","title":"Steered Generation via Gradient Descent on Sparse Features","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2504.15499","title":"Guillotine: Hypervisors for Isolating Malicious AIs","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2505.12006","title":"SOCIA-$\\nabla$: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation","created":"2025-05-17","cited_by_count":1,"area":"agents"},{"id":"2506.17369","title":"Re-Evaluating Code LLM Benchmarks Under Semantic Mutation","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2506.21288","title":"Small Encoders Can Rival Large Decoders in Detecting Groundedness","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2508.13948","title":"Prompt Orchestration Markup Language","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2509.06307","title":"Can AI Make Energy Retrofit Decisions? An Evaluation of Large Language Models","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2510.23921","title":"Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2601.22478","title":"Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.17022","title":"ReIn: Conversational Error Recovery with Reasoning Inception","created":"2026-02-19","cited_by_count":1,"area":"lr"},{"id":"2605.09271","title":"Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2605.17436","title":"Medical Context Distorts Decisions in Clinical Vision Language Models","created":"2026-05-17","cited_by_count":1,"area":"mllm"},{"id":"2607.07918","title":"Efficient Safety Alignment of Language Models via Latent Personality Traits","created":"2026-07-08","cited_by_count":1,"area":"alignment"},{"id":"2406.00509","title":"Empirical influence functions to understand the logic of fine-tuning","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2412.15404","title":"A Retrieval-Augmented Generation Framework for Academic Literature Navigation in Data Science","created":"2024-12-19","cited_by_count":0,"area":"rag"},{"id":"2412.20440","title":"Enhancing Entertainment Translation for Indian Languages using Adaptive Context, Style and LLMs","created":"2024-12-29","cited_by_count":0,"area":null},{"id":"2503.12225","title":"Interpretation Gaps in LLM-Assisted Comprehension of Privacy Documents","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2505.14880","title":"Incorporating Token Usage into Prompting Strategy Evaluation","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2506.19512","title":"heiDS at ArchEHR-QA 2025: From Fixed-k to Query-dependent-k for Retrieval Augmented Generation","created":"2025-06-24","cited_by_count":0,"area":"rag"},{"id":"2506.23930","title":"Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2507.15104","title":"AnalogFed: Privacy-Preserving Discovery of Analog Circuits at Scale with Federated Generative AI","created":"2025-07-20","cited_by_count":0,"area":null},{"id":"2509.05719","title":"Exploring Subjective Tasks in Farsi: A Survey Analysis and Evaluation of Language Models","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2510.18551","title":"SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation","created":"2025-10-21","cited_by_count":0,"area":"agents"},{"id":"2512.23028","title":"An Architecture-Led Hybrid Report on Body Language Detection Project","created":"2025-12-28","cited_by_count":0,"area":"mllm"},{"id":"2602.03358","title":"GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.05524","title":"AI Agent Systems for Supply Chains: Structured Decision Prompts and Memory Retrieval","created":"2026-02-05","cited_by_count":0,"area":"agents"},{"id":"2602.07077","title":"CALM: Class-Conditional Sparse Attention Vectors for Large Audio-Language Models","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.11179","title":"From Instruction to Output: The Role of Prompting in Modern NLG","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2604.11655","title":"RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2605.15768","title":"ALSO: Adversarial Online Strategy Optimization for Social Agents","created":"2026-05-15","cited_by_count":0,"area":"agents"},{"id":"2605.23040","title":"Steered Generation via Gradient-Based Optimization on Sparse Query Features","created":"2026-05-21","cited_by_count":0,"area":"mechinterp"},{"id":"2606.07237","title":"When Large Language Models Fail in Healthcare: Evaluating Sensitivity to Prompt Variations","created":"2026-06-05","cited_by_count":0,"area":"safety"},{"id":"2606.15521","title":"Emergent retokenization symmetry in large language models: phenomenology and applications","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2608.01193","title":"Humans Are More Diverse: Frontier LLMs Show Extreme Policies in Idealised AI Development Races","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.26222","title":"NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation","created":"2026-08-26","cited_by_count":0,"area":"alignment"},{"id":"2609.08861","title":"API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.20139","title":"Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models","created":"2026-09-17","cited_by_count":0,"area":"mllm"},{"id":"2609.38256","title":"Framing the Narrative: Ideological Mimicry in Large Language Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01428","title":"Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05463","title":"Human-Like Attention? A Psychophysical Comparison of Visual Search in Humans and MLLMs","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.19084","title":"Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19856","title":"Lost in the Fallback: How Reliably Do Typed Decision Models Use Fallback Options?","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}