Machine Translation Digest for Jul 04 2025
Here is today's selection of cs.CL papers, highlighting advancements in machine translation and language processing. The common theme revolves around enhancing translation accuracy and understanding through innovative frameworks and benchmarks, addressing challenges like ambiguous terminology and document-level context. These studies reflect a growing interest in refining AI's ability to handle nuanced language tasks, including emotional understanding and paraphrase generation.
Learning to Translate Ambiguous Terminology by Preference Optimization on Post-Edits
In real world translation scenarios, terminology is rarely one-to-one. Instead, multiple valid translations may appear in a terminology dictionary, but correctness of a translation depends on corporate style guides and context. This can be challenging for neural machine translation (NMT) systems. Luckily, in a corporate context, many examples of human post-edits of valid but incorrect terminology exist. The goal of this work is to learn how to disambiguate our terminology based on these corrections. Our approach is based on preference optimization, using the term post-edit as the knowledge to be preferred. While previous work had to rely on unambiguous translation dictionaries to set hard constraints during decoding, or to add soft constraints in the input, our framework requires neither one-to-one dictionaries nor human intervention at decoding time. We report results on English-German post-edited data and find that the optimal combination of supervised fine-tuning and preference optimization, with both term-specific and full sequence objectives, yields statistically significant improvements in term accuracy over a strong NMT baseline without significant losses in COMET score. Additionally, we release test sets from our post-edited data and terminology dictionary.
GRAFT: A Graph-based Flow-aware Agentic Framework for Document-level Machine Translation
Document level Machine Translation (DocMT) approaches often struggle with effectively capturing discourse level phenomena. Existing approaches rely on heuristic rules to segment documents into discourse units, which rarely align with the true discourse structure required for accurate translation. Otherwise, they fail to maintain consistency throughout the document during translation. To address these challenges, we propose Graph Augmented Agentic Framework for Document Level Translation (GRAFT), a novel graph based DocMT system that leverages Large Language Model (LLM) agents for document translation. Our approach integrates segmentation, directed acyclic graph (DAG) based dependency modelling, and discourse aware translation into a cohesive framework. Experiments conducted across eight translation directions and six diverse domains demonstrate that GRAFT achieves significant performance gains over state of the art DocMT systems. Specifically, GRAFT delivers an average improvement of 2.8 d BLEU on the TED test sets from IWSLT2017 over strong baselines and 2.3 d BLEU for domain specific translation from English to Chinese. Moreover, our analyses highlight the consistent ability of GRAFT to address discourse level phenomena, yielding coherent and contextually accurate translations.
WETBench: A Benchmark for Detecting Task-Specific Machine-Generated Text on Wikipedia
Given Wikipedia's role as a trusted source of high-quality, reliable content, concerns are growing about the proliferation of low-quality machine-generated text (MGT) produced by large language models (LLMs) on its platform. Reliable detection of MGT is therefore essential. However, existing work primarily evaluates MGT detectors on generic generation tasks rather than on tasks more commonly performed by Wikipedia editors. This misalignment can lead to poor generalisability when applied in real-world Wikipedia contexts. We introduce WETBench, a multilingual, multi-generator, and task-specific benchmark for MGT detection. We define three editing tasks, empirically grounded in Wikipedia editors' perceived use cases for LLM-assisted editing: Paragraph Writing, Summarisation, and Text Style Transfer, which we implement using two new datasets across three languages. For each writing task, we evaluate three prompts, generate MGT across multiple generators using the best-performing prompt, and benchmark diverse detectors. We find that, across settings, training-based detectors achieve an average accuracy of 78%, while zero-shot detectors average 58%. These results show that detectors struggle with MGT in realistic generation scenarios and underscore the importance of evaluating such models on diverse, task-specific data to assess their reliability in editor-driven contexts.
SMCLM: Semantically Meaningful Causal Language Modeling for Autoregressive Paraphrase Generation
This article introduces semantically meaningful causal language modeling (SMCLM), a selfsupervised method of training autoregressive models to generate semantically equivalent text. Our approach involves using semantically meaningful text representation as an initial embedding in the autoregressive training and generation processes. The extensive empirical study demonstrates that the SMCLM approach makes autoregressive models capable of learning robust and high-quality paraphrase generation. The proposed method is competitive with the supervised method and achieves state-of-the-art results in unsupervised approaches. This article also presents a comprehensive set of automatic metrics that cover a wide range of autogenerated paraphrase evaluation aspects. Simultaneously, this article highlights the low reliability of the metrics that are widely used in paraphrase generation evaluation, including BLEU, ROUGE, and BERTScore.
H2HTalk: Evaluating Large Language Models as Emotional Companion
As digital emotional support needs grow, Large Language Model companions offer promising authentic, always-available empathy, though rigorous evaluation lags behind model advancement. We present Heart-to-Heart Talk (H2HTalk), a benchmark assessing companions across personality development and empathetic interaction, balancing emotional intelligence with linguistic fluency. H2HTalk features 4,650 curated scenarios spanning dialogue, recollection, and itinerary planning that mirror real-world support conversations, substantially exceeding previous datasets in scale and diversity. We incorporate a Secure Attachment Persona (SAP) module implementing attachment-theory principles for safer interactions. Benchmarking 50 LLMs with our unified protocol reveals that long-horizon planning and memory retention remain key challenges, with models struggling when user needs are implicit or evolve mid-conversation. H2HTalk establishes the first comprehensive benchmark for emotionally intelligent companions. We release all materials to advance development of LLMs capable of providing meaningful and safe psychological support.
| Curated by yukajii.com |