{"total":44,"rows":[{"id":"2309.08958","title":"Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca","created":"2023-09-16","cited_by_count":60,"area":null},{"id":"2309.07098","title":"Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding","created":"2023-09-13","cited_by_count":42,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39,"area":null},{"id":"2312.12683","title":"Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?","created":"2023-12-20","cited_by_count":39,"area":null},{"id":"2402.13137","title":"The Hidden Space of Transformer Language Adapters","created":"2024-02-20","cited_by_count":17,"area":null},{"id":"2410.23825","title":"GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages","created":"2024-10-31","cited_by_count":16,"area":null},{"id":"2503.10267","title":"An Expanded Massive Multilingual Dataset for High-Performance Language Technologies (HPLT)","created":"2025-03-13","cited_by_count":16,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2406.06263","title":"MaskLID: Code-Switching Language Identification through Iterative Masking","created":"2024-06-10","cited_by_count":11,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2501.06374","title":"AFRIDOC-MT: Document-level MT Corpus for African Languages","created":"2025-01-10","cited_by_count":11,"area":null},{"id":"2412.03331","title":"LuxEmbedder: A Cross-Lingual Approach to Enhanced Luxembourgish Sentence Embeddings","created":"2024-12-04","cited_by_count":7,"area":null},{"id":"2508.13079","title":"DocHPLT: A Massively Multilingual Document-Level Translation Dataset","created":"2025-08-18","cited_by_count":7,"area":null},{"id":"2511.01066","title":"HPLT 3.0: Very Large-Scale Multilingual Resources for LLMs and MT. Mono- and Bi-lingual Data, Multilingual Evaluation, and Pre-Trained Models","created":"2025-11-02","cited_by_count":7,"area":null},{"id":"2311.09696","title":"Fumbling in Babel: An Investigation into ChatGPT's Language Identification Ability","created":"2023-11-16","cited_by_count":6,"area":null},{"id":"2403.09892","title":"Geographically-Informed Language Identification","created":"2024-03-14","cited_by_count":6,"area":null},{"id":"2405.11937","title":"Chasing COMET: Leveraging Minimum Bayes Risk Decoding for Self-Improving Machine Translation","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2504.01542","title":"Register Always Matters: Analysis of LLM Pretraining Data Through the Lens of Language Variation","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2506.15304","title":"ConLID: Supervised Contrastive Learning for Low-Resource Language Identification","created":"2025-06-18","cited_by_count":6,"area":null},{"id":"2601.18026","title":"CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data","created":"2026-01-25","cited_by_count":6,"area":null},{"id":"2602.13139","title":"OpenLID-v3: Improving the Precision of Closely Related Language Identification -- An Experience Report","created":"2026-02-13","cited_by_count":5,"area":null},{"id":"2402.01505","title":"Code-Switched Language Identification is Harder Than You Think","created":"2024-02-02","cited_by_count":3,"area":null},{"id":"2501.06892","title":"Language Fusion for Parameter-Efficient Cross-lingual Transfer","created":"2025-01-12","cited_by_count":3,"area":null},{"id":"2509.17768","title":"DIVERS-Bench: Evaluating Language Identification Across Domain Shifts and Code-Switching","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2410.08728","title":"From N-grams to Pre-trained Multilingual Models For Language Identification","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2502.06692","title":"Multi-label Scandinavian Language Identification (SLIDE)","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2602.17655","title":"What Language is This? Ask Your Tokenizer","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2404.08345","title":"FastSpell: the LangId Magic Spell","created":"2024-04-12","cited_by_count":1,"area":null},{"id":"2405.11942","title":"FAME-MT Dataset: Formality Awareness Made Easy for Machine Translation Purposes","created":"2024-05-20","cited_by_count":1,"area":null},{"id":"2504.21540","title":"Improving Informally Romanized Language Identification","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2512.11192","title":"SciLaD: A Large-Scale, Transparent, Reproducible Dataset for Natural Scientific Language Processing","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2603.10789","title":"LuxBorrow: From Pompier to Pompjee, Tracing Borrowing in Luxembourgish","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.02135","title":"GaelEval: Benchmarking LLM Performance for Scottish Gaelic","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2605.18232","title":"SomaliWeb v1: A Quality-Filtered Somali Web Corpus with a Matched Tokenizer and a Public Language-Identification Benchmark","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.23721","title":"Is a Document Educational or Just Wikipedia-Style? -- Pitfalls of Classifier-Based Quality Filtering","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2503.06547","title":"Kr\\'eyoLID From Language Identification Towards Language Mining","created":"2025-03-09","cited_by_count":0,"area":null},{"id":"2601.13346","title":"AfroScope: A Framework for Studying the Linguistic Landscape of Africa","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.08951","title":"How Should We Model the Probability of a Language?","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.17976","title":"ltzGLUE: Luxembourgish General Language Understanding Evaluation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2606.06088","title":"CHALIS: A Challenge Dataset for Language Identification in Difficult Scenarios","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2608.00581","title":"Loanword or Switch? The Annotation Boundary, Not the Model, Drives Kazakh-Russian Code-Switching Identification","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.05099","title":"Improving Language Identification for Code-Switched Utterances with Integer Linear Programming","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.16601","title":"MixLID: Token-Level Language Identification in Mixed-Language Text","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}