Tootfinder

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals
Cheng Chen, Haiyan Yin, Ivor Tsang
https://arxiv.org/abs/2509.08809

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals
Large Language Models (LLMs), when paired with prompt-based tasks, have significantly reduced data annotation costs and reliance on human annotators. However, evaluating the quality of their annotations remains challenging in dynamic, unsupervised environments where oracle feedback is scarce and conventional methods fail. To address this challenge, we propose a novel agentic annotation paradigm, where a student model collaborates with a noisy teacher (the LLM) to assess and refine annotation qu…

China opens an investigation into Qualcomm's acquisition of Autotalks, a chipmaker specializing in vehicle communications, over potential antitrust violations (Vlad Savov/Bloomberg)
https://www.bloomberg.com/news/articles/2025-1…

eu_procurements: EU procurement contract networks (2008-2016)
A bipartite network of public EU procurement contracts, from 2008 to 2016, between issuing buyers (public institutions such as a ministry or city hall) and supplying winners (a private firm). Contracts are aggregated into annual snapshots, edges are annotated with contract value information. Nodes are annotated with location information, including country of origin.
This network has 839824 nodes and 4098711 edges.

GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts
Jenna Kang, Maria Silva, Patsorn Sangkloy, Kenneth Chen, Niall Williams, Qi Sun
https://arxiv.org/abs/2509.08818

GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts
Recent advances in probabilistic generative models have extended capabilities from static image synthesis to text-driven video generation. However, the inherent randomness of their generation process can lead to unpredictable artifacts, such as impossible physics and temporal inconsistency. Progress in addressing these challenges requires systematic benchmarks, yet existing datasets primarily focus on generative images due to the unique spatio-temporal complexities of videos. To bridge this gap…

OpenAI raised concerns about anti-competitive conduct by "entrenched companies" in a September EU meeting; source: OpenAI targeted Google, Microsoft, and Apple (Samuel Stolton/Bloomberg)
https://www.bloomberg.com/news/articles/20

OpenAI Warns EU Antitrust Watchdogs of Big Tech’s Data Dominance
OpenAI has raised concerns with European Union antitrust enforcers over potentially harmful conduct by the likes of Alphabet Inc.’s Google, Microsoft Corp. and Apple Inc.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs
Debdeep Sanyal, Manodeep Ray, Murari Mandal
https://arxiv.org/abs/2509.08000 https://arxi…

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs
The release of open-weight large language models (LLMs) creates a tension between advancing accessible research and preventing misuse, such as malicious fine-tuning to elicit harmful content. Current safety measures struggle to preserve the general capabilities of the LLM while resisting a determined adversary with full access to the model's weights and architecture, who can use full-parameter fine-tuning to erase existing safeguards. To address this, we introduce AntiDote, a bi-level optimizat…

Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation
Joachim Baumann, Paul R\"ottger, Aleksandra Urman, Albert Wendsj\"o, Flor Miriam Plaza-del-Arco, Johannes B. Gruber, Dirk Hovy
https://arxiv.org/abs/2509.08825

Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation
Large language models (LLMs) are rapidly transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis. However, LLM outputs vary significantly depending on the implementation choices made by researchers (e.g., model selection, prompting strategy, or temperature settings). Such variation can introduce systematic biases and random errors, which propagate to downstream analyses and cause Type I, Type II, Type S, or Type M errors. W…

Memo: Apple's March update to its AI training guidelines for data annotators marked DEI as a "controversial" topic and removed intolerance as "harmful" behavior (Océane Herrero/Politico)
https://www.politico.eu/article/apple-teac

Apple is teaching its artificial intelligence to adapt to the Trump era
Apple policy documents enacted by a subcontractor show how the company shifted its approach to fine-tuning its AI in March, two months after the U.S. president was inaugurated.

Sources: Meta won't propose additional changes to its pay-or-consent model in the EU, and could face fresh antitrust charges and hefty daily fines (Foo Yun Chee/Reuters)
https://www.reuters.com/sustainability/boa…