{"total":95,"rows":[{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716,"area":null},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79,"area":null},{"id":"2305.05940","title":"Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment","created":"2023-05-10","cited_by_count":71,"area":null},{"id":"2501.06346","title":"Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages","created":"2025-01-10","cited_by_count":59,"area":null},{"id":"2311.00664","title":"Latent Space Translation via Semantic Alignment","created":"2023-11-01","cited_by_count":52,"area":null},{"id":"2505.18235","title":"The Origins of Representation Manifolds in Large Language Models","created":"2025-05-23","cited_by_count":51,"area":"mechinterp"},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46,"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":"2404.06228","title":"Understanding Cross-Lingual Alignment -- A Survey","created":"2024-04-09","cited_by_count":34,"area":null},{"id":"2412.04497","title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","created":"2024-11-30","cited_by_count":27,"area":null},{"id":"2404.12444","title":"mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?","created":"2024-04-18","cited_by_count":21,"area":null},{"id":"2408.10646","title":"Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs","created":"2024-08-20","cited_by_count":21,"area":null},{"id":"2410.01335","title":"Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models","created":"2024-10-02","cited_by_count":21,"area":null},{"id":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"area":null},{"id":"2401.05792","title":"Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations","created":"2024-01-11","cited_by_count":19,"area":null},{"id":"2509.03888","title":"False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize","created":"2025-09-04","cited_by_count":19,"area":null},{"id":"2402.13137","title":"The Hidden Space of Transformer Language Adapters","created":"2024-02-20","cited_by_count":17,"area":null},{"id":"2311.09194","title":"Structural Priming Demonstrates Abstract Grammatical Representations in Multilingual Language Models","created":"2023-11-15","cited_by_count":16,"area":null},{"id":"2305.11806","title":"The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics","created":"2023-05-19","cited_by_count":15,"area":null},{"id":"2409.03662","title":"The representation landscape of few-shot learning and fine-tuning in large language models","created":"2024-09-05","cited_by_count":15,"area":null},{"id":"2305.13286","title":"How do languages influence each other? Studying cross-lingual data sharing during LM fine-tuning","created":"2023-05-22","cited_by_count":14,"area":null},{"id":"2403.05189","title":"Tracing the Roots of Facts in Multilingual Language Models: Independent, Shared, and Transferred Knowledge","created":"2024-03-08","cited_by_count":14,"area":null},{"id":"2406.09200","title":"Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations","created":"2024-06-13","cited_by_count":14,"area":null},{"id":"2410.23501","title":"All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling","created":"2024-10-30","cited_by_count":14,"area":null},{"id":"2305.02151","title":"Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space","created":"2023-05-03","cited_by_count":12,"area":null},{"id":"2507.13410","title":"Causal Language Control in Multilingual Transformers via Sparse Feature Steering","created":"2025-07-17","cited_by_count":12,"area":"mechinterp"},{"id":"2602.02464","title":"From Directions to Regions: Decomposing Activations in Language Models via Local Geometry","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2405.13816","title":"Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners","created":"2024-05-22","cited_by_count":11,"area":null},{"id":"2603.09313","title":"Curveball Steering: The Right Direction To Steer Isn't Always Linear","created":"2026-03-10","cited_by_count":11,"area":"mechinterp"},{"id":"2406.15057","title":"Latent Space Translation via Inverse Relative Projection","created":"2024-06-21","cited_by_count":10,"area":null},{"id":"2408.06273","title":"FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data","created":"2024-08-12","cited_by_count":10,"area":null},{"id":"2305.18657","title":"Representation Of Lexical Stylistic Features In Language Models' Embedding Space","created":"2023-05-29","cited_by_count":8,"area":null},{"id":"2306.02920","title":"Second Language Acquisition of Neural Language Models","created":"2023-06-05","cited_by_count":8,"area":null},{"id":"2510.01025","title":"Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2310.15269","title":"GradSim: Gradient-Based Language Grouping for Effective Multilingual Training","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2504.12187","title":"What Do Large Language Models Know? Tacit Knowledge as a Potential Causal-Explanatory Structure","created":"2025-04-16","cited_by_count":6,"area":null},{"id":"2504.13816","title":"Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations","created":"2025-04-18","cited_by_count":6,"area":null},{"id":"2210.06230","title":"Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder","created":"2022-10-12","cited_by_count":5,"area":null},{"id":"2402.13562","title":"Analysis of Multi-Source Language Training in Cross-Lingual Transfer","created":"2024-02-21","cited_by_count":5,"area":null},{"id":"2406.14678","title":"Evaluating Contextualized Representations of (Spanish) Ambiguous Words: A New Lexical Resource and Empirical Analysis","created":"2024-06-20","cited_by_count":5,"area":null},{"id":"2512.00756","title":"MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents","created":"2025-11-30","cited_by_count":5,"area":"lr"},{"id":"2605.05683","title":"Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2310.16803","title":"Language Agnostic Code Embeddings","created":"2023-10-25","cited_by_count":4,"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":"2506.01599","title":"Connecting Neural Models Latent Geometries with Relative Geodesic Representations","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2506.12450","title":"Language Surgery in Multilingual Large Language Models","created":"2025-06-14","cited_by_count":4,"area":null},{"id":"2605.23036","title":"Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection","created":"2026-05-21","cited_by_count":4,"area":"mechinterp"},{"id":"2310.20456","title":"Towards a Deep Understanding of Multilingual End-to-End Speech Translation","created":"2023-10-31","cited_by_count":3,"area":null},{"id":"2401.06620","title":"TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2506.10855","title":"Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2508.12803","title":"When Alignment Hurts: Decoupling Representational Spaces in Multilingual Models","created":"2025-08-18","cited_by_count":3,"area":null},{"id":"2310.13228","title":"The Less the Merrier? Investigating Language Representation in Multilingual Models","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2406.09140","title":"Investigating the translation capabilities of Large Language Models trained on parallel data only","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2409.18199","title":"LangSAMP: Language-Script Aware Multilingual Pretraining","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2503.11280","title":"High-Dimensional Interlingual Representations of Large Language Models","created":"2025-03-14","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":"2601.12731","title":"A Shared Geometry of Difficulty in Multilingual Language Models","created":"2026-01-19","cited_by_count":2,"area":"mechinterp"},{"id":"2605.01381","title":"A framework for analyzing concept representations in neural models","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2406.14183","title":"Latent Functional Maps: a spectral framework for representation alignment","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2504.11183","title":"Bias Beyond English: Evaluating Social Bias and Debiasing Methods in a Low-Resource Setting","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2505.15090","title":"DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.17071","title":"What's in a prompt? Language models encode literary style in prompt embeddings","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2510.09790","title":"Mapping Semantic & Syntactic Relationships with Geometric Rotation","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2605.12960","title":"DiM\\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging","created":"2026-05-13","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":"2608.12334","title":"Steering the Language Axis: From Linear Decodability to Causal Control","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2303.15697","title":"Model and Evaluation: Towards Fairness in Multilingual Text Classification","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2305.13684","title":"mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2410.00513","title":"Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2410.16006","title":"Exploring Continual Fine-Tuning for Enhancing Language Ability in Large Language Model","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2503.20278","title":"The cell as a token: high-dimensional geometry in language models and cell embeddings","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2505.22506","title":"Sparsification and Reconstruction from the Perspective of Representation Geometry","created":"2025-05-28","cited_by_count":0,"area":"mechinterp"},{"id":"2601.21587","title":"A Study of Crosslinguistic Influence in Language Models","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.05035","title":"Capacity Constraints and the Multilingual Penalty for Lexical Disambiguation","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.02258","title":"Universal Conceptual Structure in Neural Translation: Probing NLLB-200's Multilingual Geometry","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2604.07095","title":"Multilingual Embedding Probes Fail to Generalize Across Learner Corpora","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.10627","title":"Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2605.22202","title":"Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.24077","title":"LWM-CDE: A Representation Space for Wireless Data Reasoning and Transferability","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.25384","title":"GeoMathCode: Understanding Interleaved Math-Code Reasoning for Geometry Problem Solving","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2606.01800","title":"Multilinguality of Large Language Models From a Structural Perspective","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.05613","title":"Multilingual Fine-Tuning via Localized Gradient Conflict Resolution","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.13934","title":"Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.14347","title":"When Language Representations Interact: Separability and Cross-Lingual Effects in LLMs","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2608.04904","title":"Strengthening Target-Language Features: SAE-Based Steering for Multilingual Inference","created":"2026-08-05","cited_by_count":0,"area":"mechinterp"},{"id":"2608.17088","title":"There is No Theoretical Curse of Multilinguality For Embedding Space Structure","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.22363","title":"Analyzing and Mitigating Cross-Lingual Degradation in Multilingual Medical VQA","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.27115","title":"Cross-Lingual Alignment Without Joint Training: Do Monolingual Language Models Converge on Universal Representations?","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.30725","title":"Where Do Multilingual Vision-Language Encoders Fail on Low-Resource Languages?","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.06381","title":"Cross-Lingual Representation Alignment by Token-Level Optimal Transport in a Language-Agnostic Space","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.16967","title":"Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control","created":"2026-09-15","cited_by_count":0,"area":"mechinterp"},{"id":"2609.22633","title":"Beetle: A Bilingual Model Suite for Modelling Second-Language Processing","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2610.16273","title":"Deep Speech Representations Track Word Timing along a Low-Dimensional Circular Trajectory","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}