arXiv:2603. 24917v2 Announce Type: replace-cross Abstract: Recent work shows that standard greedy-decoding extraction methods for quantifying memorization in LLMs miss how extraction risk varies across sequences.
arXiv:2602. 18733v2 Announce Type: replace Abstract: Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance.
Transduced language models (TLMs) combine a pretrained source language model with a finite‑state transducer to produce a language model over target strings. The paper introduces an unbiased stochastic estimator that resamples source prefixes without replacement and reweights them, allowing accurate estimation of target prefix probabilities while reducing computation compared to threshold‑pruned beam summing. Experiments on encyclopedic text, DNA, and DNA‑to‑amino‑acid transduction show improved compute–variance trade‑offs and significant runtime reductions, and the method also lowers estimated corpus surprisal in a reading‑time analysis without altering its conclusions.
arXiv:2602.07120v3 Announce Type: replace Abstract: Language models (LMs) tend to memorize portions of their training data and emit verbatim spans. When the underlying sources are sensitive or copyri...
arXiv:2605. 29223v3 Announce Type: replace Abstract: The parameter counts of the most widely used large language models (LLMs) are often withheld by their developers, leaving model size -- a primary reference point for interpreting capabilities and costs -- largely undisclosed.
The paper introduces Word-level Probability MIA (WPMIA), a black-box membership inference attack that estimates word-level generation probabilities via Monte Carlo sampling and local kernel smoothing, then aggregates them into a sequence-level likelihood estimator. By conditioning on different prefixes, WPMIA amplifies distributional differences between member and non-member texts, outperforming existing black-box baselines on open-source LLMs and achieving an average TPR@5%FPR of 42.0 on proprietary models such as GPT‑5‑Chat, Gemini‑2.5‑Flash, and Claude‑4.5‑Haiku.
Large Language Models (LLMs) raise growing concerns about privacy leakage and copyright compliance. Membership inference is a key tool for assessing such risks, but existing studies mainly focus on whether specific samples or sample-based data units are used for training.
arXiv:2606. 07996v1 Announce Type: cross Abstract: Pretraining is fundamental to the development of Large Language Models (LLMs), yet the opacity of pretraining data complicates model analysis and raises ethical, legal, and fairness concerns.
arXiv:2608. 03859v1 Announce Type: cross Abstract: Large language models (LLMs) pose challenges to academic integrity and peer review.
arXiv:2603. 18482v2 Announce Type: replace-cross Abstract: Standard decoding strategies for text generation, including top-$k$, nucleus sampling, and contrastive search, select tokens based on likelihood, restricting outputs to high-probability regions.
arXiv:2606. 06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather than whether they do so under ordinary use.
The paper introduces Grammar‑Aligned Decoding (GAD), addressing the issue that conventional grammar‑constrained decoding (GCD) can distort a large language model’s probability distribution, yielding grammatical but low‑likelihood outputs. GAD proposes an adaptive sampling method, Approximate Expected Futures (ASAp), which uses prior samples to over‑approximate future grammaticality, ensuring outputs remain both grammatical and faithful to the model’s conditional probabilities. Experiments on code generation and structured NLP tasks demonstrate that ASAp often produces higher‑likelihood outputs than existing GCD techniques while still enforcing the required grammatical constraints.
arXiv:2607. 18454v1 Announce Type: cross Abstract: Quantifying the risk of rare failures in language models, such as those triggered by adversarial distribution shifts or very large-scale deployments, requires estimating probabilities far too small for random sampling.