{"total":93,"rows":[{"id":"2506.17080","title":"Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs","created":"2025-06-20","cited_by_count":40,"area":null},{"id":"2502.04964","title":"Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistency","created":"2025-02-07","cited_by_count":30,"area":null},{"id":"2501.18251","title":"How to Select Datapoints for Efficient Human Evaluation of NLG Models?","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2502.04314","title":"BOUQuET: dataset, Benchmark and Open initiative for Universal Quality Evaluation in Translation","created":"2025-02-06","cited_by_count":22,"area":null},{"id":"2502.14301","title":"SEA-HELM: Southeast Asian Holistic Evaluation of Language Models","created":"2025-02-20","cited_by_count":19,"area":null},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2506.19571","title":"Has Machine Translation Evaluation Achieved Human Parity? The Human Reference and the Limits of Progress","created":"2025-06-24","cited_by_count":10,"area":null},{"id":"2510.24707","title":"MetricX-25 and GemSpanEval: Google Translate Submissions to the WMT25 Evaluation Shared Task","created":"2025-10-28","cited_by_count":10,"area":null},{"id":"2504.11582","title":"AskQE: Question Answering as Automatic Evaluation for Machine Translation","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2509.23067","title":"Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks","created":"2025-09-27","cited_by_count":7,"area":"synth"},{"id":"2512.16378","title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","created":"2025-12-18","cited_by_count":7,"area":null},{"id":"2601.09012","title":"TranslateGemma Technical Report","created":"2026-01-13","cited_by_count":7,"area":null},{"id":"2509.17249","title":"Extending Automatic Machine Translation Evaluation to Book-Length Documents","created":"2025-09-21","cited_by_count":6,"area":null},{"id":"2601.07338","title":"Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation","created":"2026-01-12","cited_by_count":6,"area":null},{"id":"2601.11778","title":"Translation as a Scalable Proxy for Multilingual Evaluation","created":"2026-01-16","cited_by_count":6,"area":null},{"id":"2502.14911","title":"Batayan: A Filipino NLP benchmark for evaluating Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2505.19060","title":"UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Models","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2506.08403","title":"TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration","created":"2025-06-10","cited_by_count":5,"area":"agents"},{"id":"2502.12701","title":"Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2503.24013","title":"You Cannot Feed Two Birds with One Score: the Accuracy-Naturalness Tradeoff in Translation","created":"2025-03-31","cited_by_count":4,"area":null},{"id":"2505.13036","title":"KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2509.20287","title":"Feeding Two Birds or Favoring One? Adequacy-Fluency Tradeoffs in Evaluation and Meta-Evaluation of Machine Translation","created":"2025-09-24","cited_by_count":4,"area":null},{"id":"2603.13045","title":"Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation","created":"2026-03-13","cited_by_count":4,"area":"alignment"},{"id":"2412.05862","title":"Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis","created":"2024-12-08","cited_by_count":3,"area":null},{"id":"2502.12685","title":"Theoretical Guarantees for Minimum Bayes Risk Decoding","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2505.21172","title":"TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment","created":"2025-05-27","cited_by_count":3,"area":"lr"},{"id":"2511.03295","title":"How to Evaluate Speech Translation with Source-Aware Neural MT Metrics","created":"2025-11-05","cited_by_count":3,"area":null},{"id":"2511.10984","title":"DiscoX: Benchmarking Discourse-Level Translation task in Expert Domains","created":"2025-11-14","cited_by_count":3,"area":null},{"id":"2411.15387","title":"From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2502.14429","title":"Early-Exit and Instant Confidence Translation Quality Estimation","created":"2025-02-20","cited_by_count":2,"area":"inference"},{"id":"2502.20795","title":"Test-Time Alignment for Large Language Models via Textual Model Predictive Control","created":"2025-02-28","cited_by_count":2,"area":"alignment"},{"id":"2504.19044","title":"Calibrating Translation Decoding with Quality Estimation on LLMs","created":"2025-04-26","cited_by_count":2,"area":null},{"id":"2508.10421","title":"Evaluating LLMs on Chinese Idiom Translation","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2509.04897","title":"PLaMo 2 Technical Report","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2510.22028","title":"Penalizing Length: Uncovering Systematic Bias in Quality Estimation Metrics","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2510.24664","title":"MQM Re-Annotation: A Technique for Collaborative Evaluation of Machine Translation","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2512.01316","title":"Agreement-Constrained Probabilistic Minimum Bayes Risk Decoding","created":"2025-12-01","cited_by_count":2,"area":null},{"id":"2604.17393","title":"Who Watches the Watchmen? Humans Disagree With Translation Metrics on Unseen Domains","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2605.13596","title":"Creativity Bias: How Machine Evaluation Struggles with Creativity in Literary Translations","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2412.08473","title":"Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation","created":"2024-12-11","cited_by_count":1,"area":"alignment"},{"id":"2503.05840","title":"Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2504.02106","title":"ContrastScore: Towards Higher Quality, Less Biased, More Efficient Evaluation Metrics with Contrastive Evaluation","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2505.14244","title":"TransBench: Benchmarking Machine Translation for Industrial-Scale Applications","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2508.02290","title":"A French Version of the OLDI Seed Corpus","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2508.08680","title":"TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2508.14909","title":"Preliminary Ranking of WMT25 General Machine Translation Systems","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2508.16048","title":"OpenWHO: A Document-Level Parallel Corpus for Health Translation in Low-Resource Languages","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2508.17458","title":"Evaluating the Impact of Verbal Multiword Expressions on Machine Translation","created":"2025-08-24","cited_by_count":1,"area":null},{"id":"2509.12677","title":"Case-Based Decision-Theoretic Decoding with Quality Memories","created":"2025-09-16","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":"2512.18906","title":"Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotations","created":"2025-12-21","cited_by_count":1,"area":"lr"},{"id":"2601.18006","title":"PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2602.18788","title":"BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2604.21045","title":"Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech","created":"2026-04-22","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":"2606.03259","title":"Beyond \"To whom it may concern\": Tailoring Machine Translation to Audience and Intent","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.15059","title":"A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translation","created":"2026-06-13","cited_by_count":1,"area":null},{"id":"2608.03437","title":"Dynamically Allocating Evaluation Effort for Model Ranking","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.15932","title":"Augmenting Text to Increase Translation Difficulty","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2609.04173","title":"Last Translation Benchmark","created":"2026-09-03","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":"2506.03820","title":"Automatic Correction of Writing Anomalies in Hausa Texts","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2510.07061","title":"Revisiting Metric Reliability for Fine-grained Evaluation of Machine Translation and Summarization in Indian Languages","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2601.22777","title":"RASST: Retrieval-Augmented Simultaneous Speech Translation","created":"2026-01-30","cited_by_count":0,"area":"rag"},{"id":"2602.06546","title":"MTQE.en-he: Machine Translation Quality Estimation for English-Hebrew","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.08593","title":"Kissan-Dost: Bridging the Last Mile in Smallholder Precision Agriculture with Conversational IoT","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.19840","title":"SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translation","created":"2026-02-23","cited_by_count":0,"area":"agents"},{"id":"2603.04083","title":"Hindsight Quality Prediction Experiments in Multi-Candidate Human-Post-Edited Machine Translation","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.22913","title":"Multilingual KokoroChat: A Multi-LLM Ensemble Translation Method for Creating a Multilingual Counseling Dialogue Dataset","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.29345","title":"Open Machine Translation for Esperanto","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.09916","title":"Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.19144","title":"ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2605.09098","title":"Dynamic Meta-Metrics: Source-Sentence Conditioned Weighting for MT Evaluation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.25686","title":"Testing the Deliteralization Hypothesis in Human and Machine Translation","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.00285","title":"Model-Based Quality Assessment for Massively Multilingual Parallel Data","created":"2026-05-29","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":"2606.06177","title":"Ouvia: A User-centered Framework for Measuring Usability of Speech Translation in Real-World Communication Scenarios","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.08011","title":"Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation","created":"2026-06-06","cited_by_count":0,"area":"alignment"},{"id":"2606.08748","title":"HydraQE: OSU's Submission for the IWSLT 2026 Speech Translation Metrics Shared Task","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.21413","title":"CAT-Translate: Building Compact Open-Source Models for Japanese-English Translation","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.05052","title":"Beyond Independent Labels: Schwartz-Geometry Decoding for Human Value Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.08283","title":"Do Evaluation Metrics Detect Errors in Classical Chinese to English Translations?","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.16344","title":"IndicQE-APE: A Consolidated Benchmark for Quality Estimation and Automatic Post-Editing for Indic Languages","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.18655","title":"TranslatePsy-AfriSLM: High-Quality Data Scaling For Low-Resource Machine Translation","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.20925","title":"Source-Free MT Evaluation Is Not MT Evaluation","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.00588","title":"Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Reranking","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.13611","title":"In the Blind: Building Pseudo-References for MT Evaluation","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.13916","title":"North Small Translate: Advanced Cost-Effective Translation (Cohere CAT+)","created":"2026-09-12","cited_by_count":0,"area":"moe"},{"id":"2609.14795","title":"Mind Which Bird You Favour: Parameterizing Adequacy-Fluency Balance in Meta-Evaluation of Machine Translation","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.21247","title":"When Does Reasoning Help in Machine Translation? A Hierarchical Analysis of LRM Reasoning Traces","created":"2026-09-18","cited_by_count":0,"area":"lr"},{"id":"2609.34770","title":"Reference-Grounded Data Curation for Instruction-Following Thai-English Machine Translation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35017","title":"TermJudge: A Document-Level Metric Judging, Not Counting, Terminology in Machine Translation Evaluation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.15661","title":"Feedback as an Interface: Controlling Form and Detail in LLM Translation Refinement","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}