{"total":45,"rows":[{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712,"area":null},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236,"area":null},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2412.19260","title":"MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes","created":"2024-12-26","cited_by_count":80,"area":null},{"id":"2312.03729","title":"Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?","created":"2023-11-27","cited_by_count":62,"area":null},{"id":"2205.02832","title":"Entity Cloze By Date: What LMs Know About Unseen Entities","created":"2022-05-05","cited_by_count":55,"area":null},{"id":"2407.12994","title":"A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks","created":"2024-07-17","cited_by_count":47,"area":null},{"id":"2305.03695","title":"Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements","created":"2023-05-05","cited_by_count":44,"area":null},{"id":"2407.09007","title":"Benchmarking Language Model Creativity: A Case Study on Code Generation","created":"2024-07-12","cited_by_count":40,"area":null},{"id":"2402.11493","title":"Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation","created":"2024-02-18","cited_by_count":38,"area":null},{"id":"2310.14820","title":"ALCUNA: Large Language Models Meet New Knowledge","created":"2023-10-23","cited_by_count":35,"area":null},{"id":"2305.10235","title":"Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility","created":"2023-05-15","cited_by_count":30,"area":null},{"id":"2310.20111","title":"Making Large Language Models Better Data Creators","created":"2023-10-31","cited_by_count":28,"area":null},{"id":"2305.09612","title":"Large Language Models are Built-in Autoregressive Search Engines","created":"2023-05-16","cited_by_count":27,"area":null},{"id":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2305.04329","title":"FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question Answering","created":"2023-05-07","cited_by_count":24,"area":null},{"id":"2407.08582","title":"On the Universal Truthfulness Hyperplane Inside LLMs","created":"2024-07-11","cited_by_count":24,"area":null},{"id":"2501.04961","title":"Demystifying Domain-adaptive Post-training for Financial LLMs","created":"2025-01-09","cited_by_count":24,"area":null},{"id":"2401.08574","title":"Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability","created":"2024-01-16","cited_by_count":22,"area":null},{"id":"2305.14824","title":"Mitigating Temporal Misalignment by Discarding Outdated Facts","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2306.05523","title":"FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-Answering","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2302.02500","title":"TempEL: Linking Dynamically Evolving and Newly Emerging Entities","created":"2023-02-05","cited_by_count":14,"area":null},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"id":"2311.15562","title":"Fully Authentic Visual Question Answering Dataset from Online Communities","created":"2023-11-27","cited_by_count":9,"area":null},{"id":"2505.01595","title":"Always Tell Me The Odds: Fine-grained Conditional Probability Estimation","created":"2025-05-02","cited_by_count":9,"area":null},{"id":"2509.22854","title":"Train Once, Reuse Everywhere: Generalizable Implicit In-Context Learning by Routing Attention","created":"2025-09-26","cited_by_count":8,"area":null},{"id":"2210.03273","title":"A Unified Encoder-Decoder Framework with Entity Memory","created":"2022-10-07","cited_by_count":7,"area":null},{"id":"2212.10012","title":"Language Modeling with Latent Situations","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2212.08192","title":"The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources in Natural Language Understanding Systems","created":"2022-12-15","cited_by_count":4,"area":null},{"id":"2305.05921","title":"Decker: Double Check with Heterogeneous Knowledge for Commonsense Fact Verification","created":"2023-05-10","cited_by_count":4,"area":null},{"id":"2309.09444","title":"Investigating Zero- and Few-shot Generalization in Fact Verification","created":"2023-09-18","cited_by_count":4,"area":null},{"id":"2409.02228","title":"Unforgettable Generalization in Language Models","created":"2024-09-03","cited_by_count":4,"area":null},{"id":"2309.08873","title":"X-PARADE: Cross-Lingual Textual Entailment and Information Divergence across Paragraphs","created":"2023-09-16","cited_by_count":3,"area":null},{"id":"2605.13339","title":"Probing Persona-Dependent Preferences in Language Models","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2308.00946","title":"Teaching Smaller Language Models To Generalise To Unseen Compositional Questions","created":"2023-08-02","cited_by_count":2,"area":null},{"id":"2411.03964","title":"What Really is Commonsense Knowledge?","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2608.12342","title":"Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2505.24147","title":"Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2511.17161","title":"The PLLuM Instruction Corpus","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2605.16023","title":"Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2608.20607","title":"JuryProbe: An Empirical Consensus-Risk Diagnostic for Routing Reference-Free Factuality Judge Panels to Grounded Verification","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2406.09967","title":"Bag of Lies: Robustness in Continuous Pre-training BERT","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2411.16985","title":"Teaching Smaller Language Models To Generalise To Unseen Compositional Questions (Full Thesis)","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2607.07047","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}