mlsanityData to 7 Oct 2026

Probabilistic Reasoning with LLMs for k-anonymity Estimation

arXiv 2503.09674 ↗First posted 12 Mar 2025cs.CL cs.LGcited by 2

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

Probabilistic reasoning is a key aspect of both human and artificial intelligence that allows for handling uncertainty and ambiguity in decision-making. In this paper, we introduce a new numerical reasoning task under uncertainty for large language models, focusing on estimating the privacy risk of user-generated documents containing privacy-sensitive information. We propose BRANCH, a new LLM methodology that estimates the k-privacy value of a text-the size of the population matching the given information. BRANCH factorizes a joint probability distribution of personal information as random variables. The probability of each factor in a population is estimated separately using a Bayesian network and combined to compute the final k-value. Our experiments show that this method successfully estimates the k-value 73% of the time, a 13% increase compared to o3-mini with chain-of-thought reasoning. We also find that LLM uncertainty is a good indicator for accuracy, as high-variance predictions are 37.47% less accurate on average.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 2 of its 94 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

2 of 94 references.

References · 2

  1. 2023MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoningcited by 155
  2. 2024Let's Think Var-by-Var: Large Language Models Enable Ad Hoc Probabilistic Reasoningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026ReThinker: Scientific Reasoning by Rethinking with Guided Reflection and Confidence Controlcited by 4
  2. 2026Beyond Direct Identifiers: Probabilistic Privacy Risk Estimation for Privacy-Conscious LLM Query Delegationcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
  2. 2025SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation
  3. 2025LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data
  4. 2023Beyond Memorization: Violating Privacy Via Inference with Large Language Models
  5. 2025Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefs
  6. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
  7. 2026Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs
  8. 2025Auditing M-LLMs for Privacy Risks: A Synthetic Benchmark and Evaluation Framework ↗