arXiv:2606. 24890v2 Announce Type: replace-cross Abstract: Can a small group of volunteers shape how AI systems discuss animal welfare, just by editing Wikipedia?
arXiv:2609.01182v1 Announce Type: new Abstract: Flagship language models appear saturated on benchmarks like MMLU (Hendrycks et al., 2021), scoring above 90% - yet benchmarks test only what the exper...
LMEnt is a toolkit designed to study how language models acquire and represent world knowledge. It includes a richly annotated pretraining corpus, an improved entity-based retrieval method, and twelve pretrained models with numerous checkpoints. The suite enables controlled experiments linking entity mentions in training data to downstream knowledge performance, revealing how co-occurrence patterns influence learning and editing difficulty.
The paper demonstrates that fine‑tuning large language models on a single author’s works can trigger the models to reproduce large verbatim excerpts from copyrighted books, even when prompted only with semantic descriptions. Experiments on GPT‑4o, Gemini‑2.5‑Pro, and DeepSeek‑V3.1 show up to 85‑90% recall of held‑out books, with spans exceeding 460 words, and this effect generalizes across authors and model providers. The findings suggest that fine‑tuning reactivates latent memorization from pre‑training, revealing a widespread vulnerability in industry models.
arXiv:2603.04317v2 Announce Type: replace-cross Abstract: A growing literature shows that variables can be linearly decoded from the activations of large language models (LLMs). These range from prop...
The study investigates whether large language models (LLMs) rely on textual evidence or on their pre‑existing knowledge when annotating text. Using counterfactual prompts for 995 public figures, the authors find that LLMs often default to memory shortcuts—providing correct facts about a figure even when the text contains no supporting evidence. These shortcuts are amplified by evaluation design and incentives, but can be mitigated by name reminders or masking, though with trade‑offs in gender annotation.
arXiv:2610.28092v1 Announce Type: cross Abstract: Persuasive writing exploits cognitive biases, recruiting a reader's mental shortcuts to shape belief, often without the reader noticing. We call the...
arXiv:2606. 19625v2 Announce Type: replace-cross Abstract: We use training-data attribution as an interpretable tool for capability discovery, mapping which regions of the pretraining corpus support social-reasoning versus STEM-reasoning in OLMo3-7B.
DeGenTWeb is a system that identifies websites whose informational prose is largely machine‑generated text (MGT) with minimal human input. By adapting MGT detectors for web pages and aggregating results across sites, the study reports that 20.9% of Common Crawl‑archived sites (Jan–Jul 2026) and 13.6% of Bing‑linked sites (2025) are MGT‑dominant, with a 0.12% mislabeling rate for human‑authored sites. The prevalence of MGT‑dominant sites is increasing over time and many share the same owner.
The paper introduces ATLAS, a likelihood‑based method for model authorship attribution (MAA) that learns how each source family generates text and attributes new text by comparing token‑level likelihoods. It also presents MAABench, a benchmark for evaluating MAA under out‑of‑distribution scenarios such as unseen domains and future model versions. Experiments show ATLAS outperforms existing baselines, achieving 74.27% accuracy on the hardest MAABench setting and correctly identifying teacher models in distillation experiments.
arXiv:2609.37616v1 Announce Type: new Abstract: Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on th...
arXiv:2610.31894v1 Announce Type: new Abstract: Recent Sparse Autoencoders (SAEs) decompose the representations of large language models (LLMs) into interpretable features, enabling precise readout a...
arXiv:2609.24885v1 Announce Type: new Abstract: When a language model answers from a curated corpus via graph-based retrieval, a large grounding uplift does not establish reasoning over the retrieved...