{"total":48,"rows":[{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2505.17306","title":"Refusal Direction is Universal Across Safety-Aligned Languages","created":"2025-05-22","cited_by_count":38,"area":null},{"id":"2504.03022","title":"The Dual-Route Model of Induction","created":"2025-04-03","cited_by_count":24,"area":null},{"id":"2505.20546","title":"Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline","created":"2025-05-26","cited_by_count":21,"area":null},{"id":"2507.22608","title":"Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation","created":"2025-07-30","cited_by_count":17,"area":null},{"id":"2506.22724","title":"The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure","created":"2025-06-28","cited_by_count":10,"area":null},{"id":"2507.14239","title":"CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation","created":"2025-07-17","cited_by_count":9,"area":null},{"id":"2509.09101","title":"TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla","created":"2025-09-11","cited_by_count":6,"area":null},{"id":"2505.16134","title":"Beyond Early-Token Bias: Model-Specific and Language-Specific Position Effects in Multilingual LLMs","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2601.22851","title":"When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2505.14990","title":"Language Specific Knowledge: Do Models Know Better in X than in English?","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2509.17701","title":"Investigating Bias: A Multilingual Pipeline for Generating, Solving, and Evaluating Math Problems with LLMs","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2510.10280","title":"On the Entity-Level Alignment in Crosslingual Consistency","created":"2025-10-11","cited_by_count":4,"area":null},{"id":"2506.21445","title":"Text2Cypher Across Languages: Evaluating and Finetuning LLMs","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2507.06306","title":"Humans overrely on overconfident language models, across languages","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2508.11017","title":"Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2510.05678","title":"Gradual Code-Switching as Inference-Time Cross-Lingual Representational Alignment for LLMs","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2510.06107","title":"Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2601.20009","title":"LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them?","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2603.18557","title":"Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2604.05090","title":"Multilingual Language Models Encode Script Over Linguistic Structure","created":"2026-04-06","cited_by_count":3,"area":null},{"id":"2601.18129","title":"Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2602.15038","title":"Indic-TunedLens: Interpreting Multilingual Models in Indian Languages","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2510.17001","title":"Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2602.20065","title":"Multilingual Large Language Models do not comprehend all natural languages to equal degrees","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2605.31220","title":"Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.06586","title":"PolyFact: Comparing Consistency-Driven Post-training Methods for Cross-Lingual Factual Recall","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2607.18348","title":"An Analysis of Residual-Stream Geometry Across Transformer Depth","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2609.01936","title":"Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2505.17747","title":"Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Tasks","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2509.10860","title":"Quantifier Scope Interpretation in Language Learners and LLMs","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2511.01907","title":"Between Myths and Metaphors: Rethinking LLMs for SRH in Conservative Contexts","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2601.12549","title":"Benchmarking Concept-Spilling Across Languages in LLMs","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2601.16097","title":"Incremental Multilingual Text2Cypher with Adapter Combination","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.22453","title":"Identifying Crucial Attention Heads for Multilingual Language Models: Retrieval and Retrieval-Transition Heads","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2604.13286","title":"English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2607.18691","title":"Semantic Primes as Explanans for Emotion in Large Language Models","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.00207","title":"Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.15964","title":"LLMs Get Smarter from Targeted Synthetic Multilingual Data","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.17399","title":"An Investigation of Translationese in the Generations of Multilingual Large Language Models","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.17694","title":"GADR: Gathering Architecture Decision Records from Meeting Transcriptions","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.29613","title":"Cross-lingual Functional Vectors for Emotion Detection in Large Language Models","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.01356","title":"Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.04819","title":"A Systematic Comparison of Multilingual Interpretability Methods Reveals Anisotropy-Driven Failures","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.09349","title":"SWORD: Wikidata-based Distortions Reveal Hidden Cross-Lingual Inconsistencies in LLM Factual Error Rejection","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.10993","title":"Distribution-aware Language Neuron Identification in Multilingual Large Language Models","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.20832","title":"TatBLiMP: A Benchmark of Linguistic Minimal Pairs for Tatar","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2610.06216","title":"Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}