PPDL: LLM-Based Flows as Probabilistic Programs
Researchers introduce PPDL, a probabilistic programming language designed to model and manage uncertainty in multi-step LLM workflows.
arXiv cs.LG — Machine Learning·7 Aug 2026
Use this view to inspect the underlying evidence corpus. For ranked developments, decision posture and interpretation, use Signals.
Raw feed or Signals?
Raw feed is chronological evidence. Signals ranks and interprets material change.
Researchers introduce PPDL, a probabilistic programming language designed to model and manage uncertainty in multi-step LLM workflows.
Research proves factorized generative models leak class information in latent style variables despite marginal distribution matching.
Researchers propose a method to detect spuriously correlated training data samples at model convergence without requiring group labels.
Researchers introduce Information Flow Networks, extending generative flow networks to solve incomplete information games.
Researchers introduce Align-RAG, demonstrating that frozen Time Series Foundation Models can perform retrieval-augmented forecasting without trained adapters.
Researchers introduced SEAM, a framework to evaluate whether local machine learning explanations assemble into a globally consistent explanation.
Researchers introduce Fast Evidential Rule Learning (FERL), a fuzzy rule method providing transparent evidence and built-in decision abstention.
A comparative study analyzes pattern detection methods to improve the interpretability of clustering outcomes in high-dimensional datasets.
Researchers propose a unified posterior risk framework to disentangle epistemic and aleatoric uncertainty, improving model evaluation.
Researchers proposed an extension to the WAIT scheduling algorithm to improve LLM inference throughput and latency under bursty workloads.
Researchers propose a six-dimensional taxonomy for post-training adaptation techniques to standardize model governance and risk assessment.
Researchers propose a text-segmentation defense methodology to detect indirect prompt injection (IPI) attacks in agentic LLM workflows.
Researchers propose an unsupervised audit framework to detect and localize errors in autonomous data-analysis agents.
Researchers propose securing AI agent cryptographic operations by isolating private keys in hardware keystores rather than memory.
Researchers have developed finite-sample guarantees for localized conformal prediction to address subgroup-specific model miscalibration.
Researchers propose TS-RAG, a framework applying retrieval-augmented generation to time series forecasting by retrieving historical reference sequences.
Researchers introduce a scalable estimation framework for high-dimensional VARMA models, overcoming traditional computational limits.
Researchers propose ASAT, a method using human feedback to dynamically adjust thresholds for detecting out-of-distribution model inputs.
Researchers propose combining speculative decoding with online learning to adapt draft models dynamically, improving LLM inference speeds.
Researchers propose Fractal KV-Cache Archives to compress key-value cache symbol streams during long-context LLM inference.
A new study reveals that human reasoning inputs bias LLM outputs, causing models to adopt and amplify incorrect or harmful user assertions.
An academic study of 4,440 evaluation runs shows GraphRAG systematically underperforms vector RAG on citation precision for complex corpora.
Researchers propose scaffold-mediated post-training, co-evolving LLM parameters and procedural scaffold graphs to internalize complex strategies.
Researchers propose "circuit anchors" to prevent self-evolving language models from losing core safety and alignment capabilities during optimization.
Researchers audited privacy leakage in multilingual RAG pipelines, finding vulnerability patterns across stages using Qwen2.5-7B.
Researchers demonstrate cross-model steering transfer, showing concept directions from one LLM can control behavior in a different model.
A research paper demonstrates that LLMs adopt cognitive biases based on user interaction history, even when instructions demand objectivity.
Researchers introduce SkillZip, a graph compression method for LLM agent skill libraries to reduce context window and inference costs.
Researchers propose FOCUS, a method to decouple LLM expert personas to prevent cross-domain behavioral leaks in risk-sensitive domains.
Researchers propose using random number generation to mitigate context-insensitive scoring bias in LLM-as-a-judge evaluation frameworks.
© 2026 OneBench: AI Insights. All rights reserved.
Evidence before opinion