The paper proposes a generation‑provenance substrate for synthetic speech research objects, binding source specifications, generated content, waveform, target, fact requirements, quality signals, review lineage, and an immutable manifest identity. It audits this substrate in a private Japanese care‑handoff pipeline, documenting 113 assets and 1.552 hours of synthetic speech with linked audio, transcripts, notes, and fact checklists, while noting selective human evidence and source‑specific gaps. The authors argue that provenance is necessary but not sufficient for behavior attribution, requiring additional frozen training runs and intervention evidence, and they provide a compact provenance contract, audit protocol, and a bounded case study.
"whyItMatters":"The study highlights the need for detailed provenance records to enable reliable auditing and attribution of synthetic data behavior, underscoring limitations in current practices and offering a structured framework for future research."
By Sidi Chang, Peiying Zhu
The paper introduces SynthSentry, a model‑agnostic method for detecting synthetic data contamination in language‑model training corpora. It computes a distributional divergence score based on lexical diversity collapse, n‑gram tail truncation, and perplexity variance across reference models, requiring no access to the generating model or synthetic labels. Experiments on English corpora contaminated by small open‑weight generators and an instruction‑tuned model show that SynthSentry ranks contamination severity accurately, maintains low false‑positive rates after calibration, and does not degrade downstream fine‑tuning performance at the tested scale.
By Praveen Kumar Myakala, Ravichandra Namburi, Sowmya Keragodu Jayaramu, Sooraj George Thomas
arXiv:2607. 23804v1 Announce Type: cross Abstract: Context attribution methods for large language models (LLMs) identify which input context contributes to the model response.
By Quoc-Huy Trinh, Lin Zhu, Sebastian Szyller
arXiv:2609.38831v1 Announce Type: new
Abstract: Model-attribution classifiers can often identify which language model produced a text, making model-specific writing patterns a signal of provenance. A...
By Haohan Yuan, Simin Chen, Xi Niu, Hanqing Guo, Depeng Xu, Haopeng Zhang
arXiv:2606. 11127v1 Announce Type: cross Abstract: Synthetic post-training pipelines commonly filter generated samples with reward models or holistic LLM judges, yet two practices remain rarely examined together: whether the filtering signal is grounded in the source evidence that induced each generation, and whether rejected samples can be systematically recovered rather than permanently discarded.
By Soham Bhattacharjee, Karun Sharma, Vinay Kumar Sankarapu, Pratinav Seth
arXiv:2601. 22651v2 Announce Type: replace-cross Abstract: Training-data attribution for vision generative models aims to identify which training data influenced a given output.
By Naoki Murata, Yuhta Takida, Chieh-Hsin Lai, Toshimitsu Uesaka, Bac Nguyen, Stefano Ermon, Yuki Mitsufuji
arXiv:2604. 01904v3 Announce Type: replace-cross Abstract: Post-hoc unauthorized-training data detection for large language models (LLMs) typically assumes a query-with-originals regime: rights holders query a target LLM with raw proprietary data and assess whether the model assigns them stronger memorization-based detection signals, e.
By Muxing Li, Zesheng Ye, Sharon Li, Feng Liu
The paper introduces a method for identifying the dominant knowledge source behind large language model (LLM) outputs, distinguishing between faithfulness violations (misuse of provided context) and factuality violations (errors in internal knowledge). A simple linear probe trained on hidden representations can reliably classify this source, and the authors present AttriWiki, a self‑supervised pipeline that generates labeled training data by prompting models to recall withheld entities or read them from context. Probes trained on AttriWiki achieve high Macro‑F1 scores across several models and datasets, generalize zero‑shot to a benchmark, and show that attribution mismatches can increase error rates by up to 70%.
"whyItMatters":"The study demonstrates that knowing the source of an LLM’s answer is crucial for effective mitigation of hallucinations, as attribution mismatches significantly raise error rates."
By Ivo Brink, Alexander Boer, Dennis Ulmer
arXiv:2606. 04928v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed across diverse applications, raising critical questions for governance, accountability, and data provenance.
By Fr\'ed\'eric Berdoz, Luca A. Lanzend\"orfer, Kaan Bayraktar, Roger Wattenhofer
arXiv:2608. 03859v1 Announce Type: cross Abstract: Large language models (LLMs) pose challenges to academic integrity and peer review.
By Peijia Guo, Wenxuan Xie, ZiGuang Li, Ming Li
arXiv:2609.14248v1 Announce Type: cross
Abstract: Faithful citation attribution begins with identifying the intended source for a scientific claim. We study this source-identification capability thro...
By Yee Man Choi, Xuehang Guo, Songcheng Cai, Yimu Wang, Yi R. Fung, Qingyun Wang
arXiv:2402. 08922v3 Announce Type: replace Abstract: Large-scale black-box models have become ubiquitous across numerous applications.
By Myeongseob Ko, Feiyang Kang, Weiyan Shi, Ming Jin, Zhou Yu, Ruoxi Jia