{"total":18,"rows":[{"id":"2410.18697","title":"How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMs","created":"2024-10-24","cited_by_count":23,"area":null},{"id":"2509.17559","title":"Specification-Aware Machine Translation and Evaluation for Purpose Alignment","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2604.18490","title":"LQM: Linguistically Motivated Multidimensional Quality Metrics for Machine Translation","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2504.15052","title":"Testing LLMs' Capabilities in Annotating Translations Based on an Error Typology Designed for LSP Translation: First Experiments with ChatGPT","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2605.25626","title":"Beyond Literal Translation: Evaluating Cultural Effectiveness in Social Media UGC","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2506.04848","title":"MockConf: A Student Interpretation Dataset: Analysis, Word- and Span-level Alignment and Baselines","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2509.20557","title":"SiniticMTError: A Machine Translation Dataset with Error Annotations for Sinitic Languages","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2512.07540","title":"Minimum Bayes Risk Decoding for Error Span Detection in Reference-Free Automatic Machine Translation Evaluation","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2605.24904","title":"Quantifying the Impact of Translation Errors on Multilingual LLM Evaluation","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2607.02235","title":"Challenges and Recommendations for LLM-as-a-Judge in Multilingual Settings and for Low-Resource Languages","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2609.08779","title":"Improving Term Evaluation in Machine Translation: Variation Matters","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2505.18683","title":"TULUN: Transparent and Adaptable Low-resource Machine Translation","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2603.25169","title":"To Write or to Automate Linguistic Prompts, That Is the Question","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.15763","title":"CompactQE: Interpretable Translation Quality Estimation via Small Open-Weight LLMs","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.18797","title":"Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.23002","title":"Machine Translation and Post-Editing: Comparative Evaluation of Different MT Systems and Post-Editor Groups in Specialised Translation","created":"2026-06-22","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":"2610.00096","title":"FACET at WMT 2026 Automated Translation Quality Evaluation Task","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}