Ouvia is a user-centered evaluation framework for speech translation usability in real-world scenarios, showing limited usability rates and the superiority of QA-based metrics.
hub
Findings of the WMT 25 general machine translation shared task: Time to stop evaluating on easy test sets
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
citation-role summary
other 1
citation-polarity summary
years
2026 19roles
other 1polarities
unclear 1representative citing papers
Automatic evaluation tools for literary translations correlate poorly with expert human judgments on creativity and exhibit bias favoring machine-translated texts.
Document-level machine translation followed by segment-level LLM refinement provides the strongest and most stable improvements in literary translation quality, mainly enhancing fluency and style rather than adequacy.
Human readers prefer human literary translations over AI-generated ones for immersion and clarity despite finding MT adequate and struggling to identify the source.
A 4B rewriting model trained with RL on downstream translation-quality gains outperforms no-rewriting and same-scale prompt-based rewriting, and roughly matches a 235B prompt-based rewriter.
Dynamic Meta-Metrics learns source-sentence conditioned combinations of MT metrics, with MLP-based and soft-conditioned versions showing gains over linear and GP ensembles on WMT data.
Reward models for LLMs frequently select socially undesirable options across four social domains, show no overall best performer, and exhibit a bias-avoidance versus context-sensitivity trade-off.
LLMs generate Xiaohongshu-style posts that elicit social comparison but show stable failures in prompt-based detection of the same reader-grounded signal.
Empirical study finds verbalized per-token confidence methods in LLMs for MT perform similarly to internal signals on error detection and calibration but show little correlation.
Multi-aspect iterative refinement with specialized LLMs generates superior literary translation data, enabling SFT and GRPO to produce LitMT-8B and LitMT-14B models scoring 67.25 and 69.07 CEA100 on MetaphorTrans, competitive with Claude Sonnet 4.5.
Lexical richness is a robust linguistic signal for AI-generated text detection across models and domains, while most other features are context-dependent.
Combines GRPO with teacher-guided on-policy distillation and introduces LongBlocks dataset to yield more stable long-context reasoning than either method alone.
Cross-lingual transfer and language-specific data efforts are interdependent and complementary for effective low-resource NLP, as demonstrated through Luxembourgish case studies and synthesis.
HAMR combines bi-level meta-learned instance reweighting with KNN-based neighborhood resampling to improve NLP performance under class imbalance, evaluated on six NER and classification benchmarks.
Compact 0.8B-7B models for bidirectional Japanese-English translation outperform large multilingual models on real-world domain benchmarks.
Introduces LLM Consumer Behavior Theory to analyze consumer behavior when LLMs serve as autonomous decision-making agents in markets.
A cascaded SimulST system using Parakeet and Qwen 3.5 with adaptive black-box policies and RAG context achieves +5.82 XCOMET-XL improvement on En→De for IWSLT 2026.
Hy-MT2 presents three new multilingual translation models that claim to outperform listed open-source and commercial systems on diverse tasks while enabling low-storage on-device use.
A feature-based decision tree with parsing-derived signals and heuristics detects LLM-generated code in a lightweight, CPU-only setup for SemEval-2026 Task 13.
citing papers explorer
-
Ouvia: A User-centered Framework for Measuring Usability of Speech Translation in Real-World Communication Scenarios
Ouvia is a user-centered evaluation framework for speech translation usability in real-world scenarios, showing limited usability rates and the superiority of QA-based metrics.
-
Creativity Bias: How Machine Evaluation Struggles with Creativity in Literary Translations
Automatic evaluation tools for literary translations correlate poorly with expert human judgments on creativity and exhibit bias favoring machine-translated texts.
-
What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation
Document-level machine translation followed by segment-level LLM refinement provides the strongest and most stable improvements in literary translation quality, mainly enhancing fluency and style rather than adequacy.
-
AI translation of literary texts is "fine", but readers still prefer human translations
Human readers prefer human literary translations over AI-generated ones for immersion and clarity despite finding MT adequate and struggling to identify the source.
-
Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation
A 4B rewriting model trained with RL on downstream translation-quality gains outperforms no-rewriting and same-scale prompt-based rewriting, and roughly matches a 235B prompt-based rewriter.
-
Dynamic Meta-Metrics: Source-Sentence Conditioned Weighting for MT Evaluation
Dynamic Meta-Metrics learns source-sentence conditioned combinations of MT metrics, with MLP-based and soft-conditioned versions showing gains over linear and GP ensembles on WMT data.
-
Misaligned by Reward: Socially Undesirable Preferences in LLMs
Reward models for LLMs frequently select socially undesirable options across four social domains, show no overall best performer, and exhibit a bias-avoidance versus context-sensitivity trade-off.
-
Psychologically Potent, Computationally Invisible: LLMs Generate Social-Comparison-Eliciting Posts They Fail to Detect
LLMs generate Xiaohongshu-style posts that elicit social comparison but show stable failures in prompt-based detection of the same reader-grounded signal.
-
Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation
Empirical study finds verbalized per-token confidence methods in LLMs for MT perform similarly to internal signals on error detection and calibration but show little correlation.
-
Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach
Multi-aspect iterative refinement with specialized LLMs generates superior literary translation data, enabling SFT and GRPO to produce LitMT-8B and LitMT-14B models scoring 67.25 and 69.07 CEA100 on MetaphorTrans, competitive with Claude Sonnet 4.5.
-
A Systematic Analysis of Linguistic Features in AI-Generated Text Detection Across Domains and Models
Lexical richness is a robust linguistic signal for AI-generated text detection across models and domains, while most other features are context-dependent.
-
A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation
Combines GRPO with teacher-guided on-policy distillation and introduces LongBlocks dataset to yield more stable long-context reasoning than either method alone.
-
Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish
Cross-lingual transfer and language-specific data efforts are interdependent and complementary for effective low-resource NLP, as demonstrated through Luxembourgish case studies and synthesis.
-
Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation
HAMR combines bi-level meta-learned instance reweighting with KNN-based neighborhood resampling to improve NLP performance under class imbalance, evaluated on six NER and classification benchmarks.
-
CAT-Translate: Building Compact Open-Source Models for Japanese-English Translation
Compact 0.8B-7B models for bidirectional Japanese-English translation outperform large multilingual models on real-world domain benchmarks.
-
LLM Consumer Behavior Theory: Foundations of a Novel Research Field
Introduces LLM Consumer Behavior Theory to analyze consumer behavior when LLMs serve as autonomous decision-making agents in markets.
-
MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task
A cascaded SimulST system using Parakeet and Qwen 3.5 with adaptive black-box policies and RAG context achieves +5.82 XCOMET-XL improvement on En→De for IWSLT 2026.
-
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
Hy-MT2 presents three new multilingual translation models that claim to outperform listed open-source and commercial systems on diverse tasks while enabling low-storage on-device use.
-
FMI_SU_Yotkova_Kastreva at SemEval-2026 Task 13: Lightweight Detection of LLM-Generated Code via Stylometric Signals
A feature-based decision tree with parsing-derived signals and heuristics detects LLM-generated code in a lightweight, CPU-only setup for SemEval-2026 Task 13.