One paper argues that LLMs can stand in for human judgment on MT quality annotation, while another shows those same models still struggle with hallucination detection in Sinhala-to-English NMT. On the evaluation side, the MQM and ESA comparison tests agreement against human annotation across language pairs and granularity levels; on the generation side, a 45,000-sample synthetic corpus built from five corruption strategies is used to probe reference-free detection of pathological hallucinations. Elsewhere, SignRAG brings retrieval-augmented gloss-free sign language translation to decoder-only LLMs, and a study of 23 LLM versions released from June 2023 to August 2026 finds that turnover weakens screening for AI-assisted scientific writing.

Large Language Models for Machine Translation Quality Annotation: Humans and Models Are Both Challenged

LLMs remain unreliable for MQM and ESA annotation across language pairs and domains, especially on fine-grained errors, so human review still matters for low-resource and variant-sensitive evaluation.

Large Language Models (LLMs) are considered to be a more efficient and cost-effective alternative to human judgment for Machine Translation (MT) evaluation. With MT evaluation spanning a large number of language pairs, domains and levels of annotation granularity, LLMs must be thoroughly evaluated across these dimensions before being reliably used as alternatives to human evaluation. In this paper, we evaluate the performance of LLMs for two prominent MT quality evaluation schemes: Multidimensional Quality Metrics (MQM) and Error Span Annotation (ESA) by comparing their agreement with human annotators. We present results on a long-context test set of 70 language pairs and the publicly available WMT23 and WMT25 data, investigating both score and error span annotation agreement across a variety of language pairs and domains. Our results show that while LLM agreement with human annotators exceeds agreement between human annotators for some evaluation tasks, both vary substantially across annotation schemes, language pairs and domains and remain unreliable for most settings. Furthermore, we identify challenges facing both human and LLM annotators: humans are particularly challenged by fine-grained MQM annotations and low-resource language pairs, while LLMs struggle with minor errors, wrong language variants and error span annotation. Our results highlight the potential for improvement for both human and LLM annotation performance, possibly through human-LLM collaborative annotation pipelines that address the reliability issues identified in this work.

Fact over Fiction: Detection of Pathological Hallucinations in Sinhala-to-English Neural Machine Translation

For Sinhala-to-English, hallucination detection works best when it uses the source sentence and semantic signals together, because mDeBERTa-v3 reaches 0.841 token F1 and detector performance collapses without source input.

Neural Machine Translation (NMT) models, while capable of producing highly fluent outputs, remain vulnerable to hallucinations, which are translations that are natural yet semantically unrelated to the source. This vulnerability is acute in low-resource settings like Sinhala-to-English, where weak cross-lingual alignment leads to hallucinations. This paper introduces a framework for reference-free hallucination detection in this language pair. We present a 45,000-sample synthetic dataset generated through a probabilistic chain of five linguistically motivated corruption strategies, with a semantic rescue mechanism that uses character-level similarity to distinguish hallucinations from morphological variants. We fine-tune mDeBERTa-v3 for token-level sequence labelling, reaching a token-level F1 of 0.841 +/- 0.001 over three seeds on a source-disjoint test set, and study a three-signal ensemble integrating neural risk scores, sequence log-probabilities, and cross-lingual semantic embeddings (LaBSE). A source-ablation control shows that the detector relies on the Sinhala source rather than on surface artefacts of the corruption process: shuffling or removing the source reduces sentence-level AUROC from 0.970 to chance. We benchmark eight NMT systems spanning five model families and find that detector firings vary by an order of magnitude across architectures.

SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation

SignRAG suggests gloss-free sign translation can benefit from retrieval-augmented decoder-only LLMs, with hierarchical pretraining and utility-guided fine-tuning beating gloss-supervised methods across benchmarks.

Contemporary decoder-only large language models (LLMs) have demonstrated strong capabilities across a wide range of domains. However, existing pretraining paradigms for gloss-free sign language translation (SLT) are largely designed around conventional encoder-decoder pretrained language models, which limits their direct applicability to decoder-only LLMs. To address this limitation, we propose SignRAG, a unified framework combining hierarchical pretraining, target-domain retrieval augmentation, and retrieval-aware reinforcement fine-tuning. Hierarchical pretraining first learns linguistically grounded sign representations and then jointly aligns the sign encoder with an LLM, mitigating cross-modal optimization imbalance. For downstream adaptation, SignRAG complements parameter-based fine-tuning with a target-domain retrieval gallery that provides instance-specific translation cues. To ensure that retrieved contexts are used appropriately, we further introduce Retrieval Utility-Guided Reinforcement Fine-Tuning (RUG-RFT), which combines translation-quality and retrieval-utility rewards to encourage beneficial retrieval use while suppressing harmful reliance. Experiments on multiple SLT benchmarks establish new state-of-the-art performance. In particular, to the best of our knowledge, SignRAG is the first gloss-free approach to outperform gloss-supervised methods across all reported metrics on CSL-Daily. Our code has been released at GitHub, together with models of different sizes to support future academic research.

Large Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific Writing

LLM detectors for AI-written scientific text decay across model generations, so screening pipelines need continual retraining or they miss up to most rewrites of newer versions while flagging many human abstracts.

Journals and conferences have begun to screen submitted manuscripts for text written using large language models (LLMs). The reliability of this screening rests on benchmark evaluations against a fixed set of LLM versions, while the versions in actual use keep changing. Here we quantify how this LLM turnover affects the screening of scientific manuscripts. We paired 4,000 pre-ChatGPT abstracts from the Proceedings of the National Academy of Sciences with their rewrites by 23 LLM versions from three vendors, released between June 2023 and August 2026. We then trained detectors under maintenance scenarios ranging from a detector retrained on every new version to one trained once and never updated. Detectors trained only on a vendor's past versions can collapse at the boundaries between model generations: calibrated to falsely flag 1% of human-written abstracts, they catch above 99% of rewrites just before the sharpest boundary and 3.8% just after it. Detectors trained on later versions can also miss rewrites of earlier ones. Vocabulary differences between versions largely track where detection transfers and where it fails. In the two screening scenarios we simulated, screens covering all 23 versions either flagged one in eight human-written abstracts or missed one in three rewrites of the newest version. Indeed, a commercial detector missed most rewrites of the version just after the sharpest boundary while flagging almost no human-written abstracts. Research-integrity policy should therefore treat the benchmark accuracy of a detector as provisional, to be re-verified with every LLM release, including earlier versions.

Papers announced by arXiv on Thursday, 8 October 2026, covering submissions from 7 October to 8 October 2026.