{"total":53,"rows":[{"id":"2507.11407","title":"EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes","created":"2025-07-15","cited_by_count":32,"area":"lr"},{"id":"2503.12524","title":"EXAONE Deep: Reasoning Enhanced Language Models","created":"2025-03-16","cited_by_count":21,"area":"lr"},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2508.07805","title":"Can You Trick the Grader? Adversarial Persuasion of LLM Judges","created":"2025-08-11","cited_by_count":9,"area":null},{"id":"2502.08910","title":"InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU","created":"2025-02-13","cited_by_count":7,"area":"inference"},{"id":"2506.11578","title":"Efficient LLM Collaboration via Planning","created":"2025-06-13","cited_by_count":7,"area":"lr"},{"id":"2509.01324","title":"KoBLEX: Open Legal Question Answering with Multi-hop Reasoning","created":"2025-09-01","cited_by_count":7,"area":"lr"},{"id":"2503.00032","title":"KatFishNet: Detecting LLM-Generated Korean Text through Linguistic Feature Analysis","created":"2025-02-25","cited_by_count":6,"area":null},{"id":"2507.08924","title":"From KMMLU-Redux to KMMLU-Pro: A Professional Korean Benchmark Suite for LLM Evaluation","created":"2025-07-11","cited_by_count":6,"area":null},{"id":"2512.01020","title":"Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics","created":"2025-11-30","cited_by_count":5,"area":"lr"},{"id":"2501.05712","title":"Multi-Step Reasoning in Korean and the Emergent Mirage","created":"2025-01-10","cited_by_count":4,"area":"lr"},{"id":"2503.02784","title":"Do Not Trust Licenses You See: Dataset Compliance Requires Massive-Scale AI-Powered Lifecycle Tracing","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2509.24678","title":"Reference-Free Rating of LLM Responses via Latent Information","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2503.03444","title":"Taxation Perspectives from Large Language Models: A Case Study on Additional Tax Penalties","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2510.15346","title":"When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2601.21700","title":"Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2602.03183","title":"Privasis: Synthesizing the Largest \"Public\" Private Dataset from Scratch","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2602.20170","title":"CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation","created":"2026-02-09","cited_by_count":3,"area":"safety"},{"id":"2503.05721","title":"What Are They Filtering Out? An Experimental Benchmark of Filtering Strategies for Harm Reduction in Pretraining Datasets","created":"2025-02-17","cited_by_count":2,"area":"safety"},{"id":"2505.11881","title":"Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2506.01237","title":"Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2507.04748","title":"LLM-based Question-Answer Framework for Sensor-driven HVAC System Interaction","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2510.14565","title":"Assessing Socio-Cultural Alignment and Technical Safety of Sovereign LLMs","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2606.06797","title":"Korean Culture into LLM Alignment: Toward Cultural Coherence","created":"2026-06-05","cited_by_count":2,"area":"alignment"},{"id":"2503.22968","title":"Redefining Evaluation Standards: A Unified Framework for Evaluating the Korean Capabilities of Language Models","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2505.16566","title":"ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic Contexts","created":"2025-05-22","cited_by_count":1,"area":"lr"},{"id":"2506.15266","title":"Thunder-DeID: Accurate and Efficient De-identification Framework for Korean Court Judgments","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2507.05444","title":"PhoniTale: Phonologically Grounded Mnemonic Generation for Typologically Distant Language Pairs","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2507.11049","title":"Journalism-Guided Agentic In-Context Learning for News Stance Detection","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2509.17807","title":"Everyday Physics in Korean Contexts: A Culturally Grounded Physical Reasoning Benchmark","created":"2025-09-22","cited_by_count":1,"area":"lr"},{"id":"2509.20057","title":"Responsible AI Technical Report","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2604.06173","title":"Beyond Case Law: Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2604.13468","title":"From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2605.17443","title":"Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2606.19887","title":"FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming","created":"2026-06-18","cited_by_count":1,"area":"safety"},{"id":"2606.31796","title":"CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2504.01708","title":"TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2505.00060","title":"Fact-Consistency Evaluation of Text-to-SQL Generation for Business Intelligence Using Exaone 3.5","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2509.14712","title":"From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.24150","title":"Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean","created":"2025-10-28","cited_by_count":0,"area":"lr"},{"id":"2512.08480","title":"Soft Inductive Bias Approach via Explicit Reasoning Perspectives in Inappropriate Utterance Detection Using Large Language Models","created":"2025-12-09","cited_by_count":0,"area":"lr"},{"id":"2604.12377","title":"SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language Models","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.24310","title":"Discovering Lexical Gaps Using Embeddings from Multilingual LLMs","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.03014","title":"MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2606.09178","title":"Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative Analysis","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2607.17513","title":"After the Euclidean Highway: Hyperbolic Expert AI as the Next Innovation","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.13947","title":"Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.04598","title":"PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning","created":"2026-09-04","cited_by_count":0,"area":"lr"},{"id":"2609.07447","title":"An LLM-Associated Register Shift in Korean Journal Abstracts: A Morphology-Aware Excess-Vocabulary Study, 2018-2026","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.19885","title":"Evaluating Communicative Success in Machine-Translated Conversation","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.31688","title":"Don't Repeat Yourself: Self-Supervised Fine-Tuning for Coverage","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.16440","title":"ARMED: Adaptive Retrieval-Augmented Medication Recommendation","created":"2026-10-12","cited_by_count":0,"area":"rag"},{"id":"2610.19399","title":"KoAGE: Do Large Language Models Know, Learn, and Coin Korean Neologisms?","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}