{"total":47,"rows":[{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2309.17446","title":"L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models","created":"2023-09-29","cited_by_count":22,"area":null},{"id":"2509.17995","title":"Variation in Verification: Understanding Verification Dynamics in Large Language Models","created":"2025-09-22","cited_by_count":19,"area":null},{"id":"2410.01769","title":"Quantifying Generalization Complexity for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2404.14809","title":"A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applications","created":"2024-04-23","cited_by_count":17,"area":null},{"id":"2410.23299","title":"FVEval: Understanding Language Model Capabilities in Formal Verification of Digital Hardware","created":"2024-10-15","cited_by_count":10,"area":null},{"id":"2305.02230","title":"Can ChatGPT Pass An Introductory Level Functional Language Programming Course?","created":"2023-04-29","cited_by_count":9,"area":null},{"id":"2502.15776","title":"Logic.py: Bridging the Gap between LLMs and Constraint Solvers","created":"2025-02-17","cited_by_count":9,"area":null},{"id":"2502.15823","title":"InductionBench: LLMs Fail in the Simplest Complexity Class","created":"2025-02-20","cited_by_count":9,"area":null},{"id":"2511.09008","title":"A Neurosymbolic Approach to Natural Language Formalization and Verification","created":"2025-11-12","cited_by_count":9,"area":null},{"id":"2401.06786","title":"CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation","created":"2023-11-10","cited_by_count":8,"area":null},{"id":"2306.12951","title":"Public Attitudes Toward ChatGPT on Twitter: Sentiments, Topics, and Occupations","created":"2023-06-22","cited_by_count":6,"area":null},{"id":"2302.09458","title":"Learning Language Representations with Logical Inductive Bias","created":"2023-02-19","cited_by_count":5,"area":null},{"id":"2409.01495","title":"The Compressor-Retriever Architecture for Language Model OS","created":"2024-09-02","cited_by_count":5,"area":null},{"id":"2506.09433","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","created":"2025-06-11","cited_by_count":5,"area":null},{"id":"2507.16199","title":"LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty","created":"2025-07-22","cited_by_count":5,"area":null},{"id":"2510.17793","title":"Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2310.04381","title":"Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications","created":"2023-10-06","cited_by_count":4,"area":null},{"id":"2403.16097","title":"Can Language Models Pretend Solvers? Logic Code Simulation with LLMs","created":"2024-03-24","cited_by_count":4,"area":null},{"id":"2403.18327","title":"$\\forall$uto$\\exists$val: Autonomous Assessment of LLMs in Formal Synthesis and Interpretation Tasks","created":"2024-03-27","cited_by_count":3,"area":null},{"id":"2407.20513","title":"Prompt2DeModel: Declarative Neuro-Symbolic Modeling with Natural Language","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2410.03203","title":"Learning Semantic Structure through First-Order-Logic Translation","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2502.13953","title":"Benchmarking graph construction by large language models for coherence-driven inference","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2505.10844","title":"Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Models","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2508.20674","title":"Bridging Minds and Machines: Toward an Integration of AI and Cognitive Science","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2509.10249","title":"Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2509.22338","title":"Advancing Natural Language Formalization to First Order Logic with Fine-tuned LLMs","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2509.24125","title":"The Impossibility of Inverse Permutation Learning in Transformer Models","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.06307","title":"Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2604.10341","title":"VeriTrans: Fine-Tuned LLM-Assisted NL-to-PL Translation via a Deterministic Neuro-Symbolic Pipeline","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2410.12878","title":"Towards More Effective Table-to-Text Generation: Assessing In-Context Learning and Self-Evaluation with Open-Source Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2501.06286","title":"Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2505.04736","title":"The promise and limits of LLMs in constructing proofs and hints for logic problems in intelligent tutoring systems","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2606.02837","title":"Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.13767","title":"Beyond LoRA: Is Sparsity-Induced Adaptation Better?","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2607.14528","title":"Controlled Reformulation Testing for Logical Consistency in Large Language Models","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2410.14353","title":"Assistive AI for Augmenting Human Decision-making","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2502.08904","title":"MIH-TCCT: Mitigating Inconsistent Hallucinations in LLMs via Event-Driven Text-Code Cyclic Training","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2602.01171","title":"ASP-Bench: From Natural Language to Logic Programs","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2605.17911","title":"A Pilot Benchmark for NL-to-FOL Translation in Planetary Exploration","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.23386","title":"Confidently Wrong: Exception Chain Collapse in Frontier LLM Rule Evaluation","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2609.09081","title":"Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.38621","title":"When Scientific Contradictions Are Lost in Translation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02190","title":"Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02792","title":"Law And Order: Tax Law Autoformalization","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}