{"total":64,"rows":[{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894,"area":"lr"},{"id":"2404.18796","title":"Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models","created":"2024-04-29","cited_by_count":326,"area":null},{"id":"2305.14283","title":"Query Rewriting for Retrieval-Augmented Large Language Models","created":"2023-05-23","cited_by_count":213,"area":"rag"},{"id":"2306.04136","title":"Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering","created":"2023-06-07","cited_by_count":119,"area":null},{"id":"2304.10513","title":"Why Does ChatGPT Fall Short in Providing Truthful Answers?","created":"2023-04-20","cited_by_count":54,"area":null},{"id":"2407.13101","title":"Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach","created":"2024-07-18","cited_by_count":40,"area":"rag"},{"id":"2406.17169","title":"Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models","created":"2024-06-24","cited_by_count":39,"area":"lr"},{"id":"2310.05253","title":"Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models","created":"2023-10-08","cited_by_count":37,"area":"lr"},{"id":"2311.07138","title":"WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models","created":"2023-11-13","cited_by_count":32,"area":"safety"},{"id":"2407.12402","title":"TurkishMMLU: Measuring Massive Multitask Language Understanding in Turkish","created":"2024-07-17","cited_by_count":32,"area":null},{"id":"2310.13552","title":"Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning","created":"2023-10-20","cited_by_count":21,"area":"lr"},{"id":"2407.18553","title":"REAPER: Reasoning based Retrieval Planning for Complex RAG Systems","created":"2024-07-26","cited_by_count":16,"area":"lr"},{"id":"2412.10079","title":"Lost in the Middle, and In-Between: Enhancing Language Models' Ability to Reason Over Long Contexts in Multi-Hop QA","created":"2024-12-13","cited_by_count":13,"area":"lr"},{"id":"2405.15452","title":"Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top","created":"2024-05-24","cited_by_count":12,"area":null},{"id":"2504.16787","title":"Credible Plan-Driven RAG Method for Multi-Hop Question Answering","created":"2025-04-23","cited_by_count":12,"area":"rag"},{"id":"2409.08250","title":"OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering","created":"2024-09-12","cited_by_count":10,"area":null},{"id":"2603.01152","title":"DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent","created":"2026-03-01","cited_by_count":10,"area":"agents"},{"id":"2509.21199","title":"A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA","created":"2025-09-25","cited_by_count":9,"area":"lr"},{"id":"2412.07420","title":"RAG-based Question Answering over Heterogeneous Data and Text","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2601.04525","title":"GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence","created":"2026-01-08","cited_by_count":7,"area":"lr"},{"id":"2310.15372","title":"EpiK-Eval: Evaluation for Language Models as Epistemic Models","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2310.16731","title":"Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoning","created":"2023-10-25","cited_by_count":6,"area":"lr"},{"id":"2511.07364","title":"Self-Evaluating LLMs for Multi-Step Tasks: Stepwise Confidence Estimation for Failure Detection","created":"2025-11-10","cited_by_count":6,"area":null},{"id":"2502.16358","title":"Wrong Answers Can Also Be Useful: PlausibleQA -- A Large-Scale QA Dataset with Answer Plausibility Scores","created":"2025-02-22","cited_by_count":5,"area":null},{"id":"2506.02591","title":"On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures","created":"2025-06-03","cited_by_count":5,"area":"lr"},{"id":"2507.18202","title":"Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection","created":"2025-07-24","cited_by_count":5,"area":"rag"},{"id":"2510.12925","title":"Who's Asking? Evaluating LLM Robustness to Inquiry Personas in Factual Question Answering","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2212.09512","title":"Rethinking Label Smoothing on Multi-hop Question Answering","created":"2022-12-19","cited_by_count":4,"area":null},{"id":"2308.06431","title":"Performance Prediction for Multi-hop Questions","created":"2023-08-12","cited_by_count":4,"area":null},{"id":"2403.12393","title":"Dr3: Ask Large Language Models Not to Give Off-Topic Answers in Open Domain Multi-Hop Question Answering","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2412.01626","title":"WikiHint: A Human-Annotated Dataset for Hint Ranking and Generation","created":"2024-12-02","cited_by_count":4,"area":null},{"id":"2510.00024","title":"EpidemIQs: Prompt-to-Paper LLM Agents for Epidemic Modeling and Analysis","created":"2025-09-24","cited_by_count":4,"area":"agents"},{"id":"2211.08466","title":"Reasoning Circuits: Few-shot Multihop Question Generation with Structured Rationales","created":"2022-11-15","cited_by_count":3,"area":"lr"},{"id":"2504.16414","title":"Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study","created":"2025-04-23","cited_by_count":3,"area":"lr"},{"id":"2505.11811","title":"BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering","created":"2025-05-17","cited_by_count":3,"area":"lr"},{"id":"2506.14927","title":"MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance","created":"2025-06-17","cited_by_count":3,"area":"lr"},{"id":"2605.01248","title":"$S^3$-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Data","created":"2026-05-02","cited_by_count":3,"area":"lr"},{"id":"2309.12767","title":"Furthest Reasoning with Plan Assessment: Stable Reasoning Path with Retrieval-Augmented Large Language Models","created":"2023-09-22","cited_by_count":2,"area":"lr"},{"id":"2311.18151","title":"Uncertainty Guided Global Memory Improves Multi-Hop Question Answering","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2502.10976","title":"QuOTE: Question-Oriented Text Embeddings","created":"2025-02-16","cited_by_count":2,"area":"rag"},{"id":"2507.13625","title":"Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety","created":"2025-07-18","cited_by_count":2,"area":null},{"id":"2403.01969","title":"AS-ES Learning: Towards Efficient CoT Learning in Small Models","created":"2024-03-04","cited_by_count":1,"area":"lr"},{"id":"2408.15171","title":"Measuring text summarization factuality using atomic facts entailment metrics in the context of retrieval augmented generation","created":"2024-08-27","cited_by_count":1,"area":"rag"},{"id":"2412.08317","title":"Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge","created":"2024-12-11","cited_by_count":1,"area":"lr"},{"id":"2412.15101","title":"Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability","created":"2024-12-19","cited_by_count":1,"area":null},{"id":"2509.00806","title":"CaresAI at BioCreative IX Track 1 -- LLM for Biomedical QA","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2510.04293","title":"Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness","created":"2025-10-05","cited_by_count":1,"area":"rag"},{"id":"2511.17881","title":"MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2512.15922","title":"Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG Systems","created":"2025-12-17","cited_by_count":1,"area":"rag"},{"id":"2601.07422","title":"Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2601.21387","title":"User-Centric Evidence Ranking for Attribution and Fact Verification","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.03709","title":"No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2606.15971","title":"SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges","created":"2026-06-14","cited_by_count":1,"area":"lr"},{"id":"2210.15327","title":"Towards Language-driven Scientific AI","created":"2022-10-27","cited_by_count":0,"area":null},{"id":"2506.02503","title":"KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG","created":"2025-06-03","cited_by_count":0,"area":"rag"},{"id":"2506.09277","title":"NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2602.13890","title":"Evaluating Prompt Engineering Techniques for RAG in Small Language Models: A Multi-Hop QA Approach","created":"2026-02-14","cited_by_count":0,"area":"rag"},{"id":"2603.10700","title":"Structured Linked Data as a Memory Layer for Agent-Orchestrated Retrieval","created":"2026-03-11","cited_by_count":0,"area":"rag"},{"id":"2604.07929","title":"Same Outcomes, Different Journeys: A Trace-Level Framework for Comparing Human and GUI-Agent Behavior in Production Search Systems","created":"2026-04-09","cited_by_count":0,"area":"agents"},{"id":"2604.19899","title":"A Reproducibility Study of Metacognitive Retrieval-Augmented Generation","created":"2026-04-21","cited_by_count":0,"area":"rag"},{"id":"2605.31367","title":"Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.12129","title":"SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2608.27481","title":"XHotpotQA: A Benchmark for Cross-Lingual Knowledge Composition in Multi-Hop Question Answering","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.35193","title":"ConRAG: Lightweight inference of multi-hop relations","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}