Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models

• URL: http://arxiv.org/abs/2606.09856v1
• Date: Tue, 26 May 2026 15:40:02 GMT
• Title: Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models
• Abstract summary: Many realworld reasoning problems are inductive: agents must infer uncertain beliefs from sparse, ambiguous observations.<n>There are challenges to using standard finetuning methods for inductive reasoning.<n>We introduce Program Posterior Training (PPT) to address these limitations.
• Score: 10.489066116287221
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable. Yet, many real-world reasoning problems are inductive: agents must infer uncertain beliefs from sparse, ambiguous observations. There are challenges to using standard fine-tuning methods for inductive reasoning, including difficulties in curating large-scale, high-quality labeled datasets and in handling targets that are inherently distributional. In this work, we introduce a novel approach, called Program-based Posterior Training (PPT), to address these limitations: we use an LLM to generate diverse open-world scenarios as probabilistic programs, run probabilistic inference to produce distributional target responses to queries, and then fine-tune on these probabilistic soft labels. Using this approach, we fine-tune LLMs on 10,000 programmatically generated scenarios and evaluate on held-out motifs, human-labeled judgments, and external benchmarks. Overall, PPT substantially improves estimation accuracy on held-out inductive tasks, increases alignment with human judgments, and transfers to external benchmarks for estimation and calibration. Additionally, the gains in raw calibration are not subsumed by post-hoc temperature scaling, showing that the models have more deeply internalized uncertainty compared to output rescaling. Together, these results suggest that probabilistic-program-mediated fine-tuning is a promising approach for post-training LLMs to reliably perform approximate inductive inference.

Related papers

• Sound Probabilistic Safety Bounds for Large Language Models [50.060741829250645]
  We study a new application of the Clopper-Pearson confidence intervals to obtain probably approximately correct (PAC) bounds for this problem.<n>Our approach in particular enables the efficient computation of useful lower bounds, even in scenarios where the true harm probability is extremely small.
  arXiv  Detail & Related papers  (2026-07-22T15:31:28Z)
• Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inference [48.78219918881965]
  We propose a principled framework for deriving task-specific strictly proper scoring rules by matching the local curvature of the downstream error metric.<n>We apply this to the Average Treatment Effect (ATE) estimation, deriving a closed-form loss and its corresponding canonical probability mapping.
  arXiv  Detail & Related papers  (2026-06-02T08:41:25Z)
• TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning [44.20336483508951]
  Table reasoning requires models to jointly perform semantic understanding and precise numerical operations.<n>To address these limitations, we previously proposed TableMind as a tuning-based autonomous programmatic agent.<n>We extend this foundation to TableMind++ by introducing a novel uncertainty-aware inference framework.
  arXiv  Detail & Related papers  (2026-03-08T08:31:33Z)
• From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty [9.798854302346802]
  Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains.<n>We propose a three-stage pipeline to post-train LLMs to efficiently infer calibrated uncertainty estimates for their responses.<n> Experiments show that models trained with our pipeline achieve better calibration than baselines and generalize to unseen tasks without further processing.
  arXiv  Detail & Related papers  (2026-03-06T14:21:42Z)
• D-Models and E-Models: Diversity-Stability Trade-offs in the Sampling Behavior of Large Language Models [91.21455683212224]
  In large language models (LLMs), the probability of relevance for the next piece of information is linked to the probability of relevance for the next product.<n>But whether fine-grained sampling probabilities faithfully align with task requirements remains an open question.<n>We identify two model types: D-models, whose P_token exhibits large step-to-step variability and poor alignment with P_task; and E-models, whose P_token is more stable and better aligned with P_task.
  arXiv  Detail & Related papers  (2026-01-25T14:59:09Z)
• Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Models [13.41454380481593]
  Uncertainty estimation, often using predictive entropy estimation, is key to addressing this issue.<n>This paper proposes an efficient, training-free uncertainty estimation method that approximates predictive entropy using the responses' top-$K$ probabilities.
  arXiv  Detail & Related papers  (2025-11-10T23:31:43Z)
• Always Tell Me The Odds: Fine-grained Conditional Probability Estimation [37.950889606305836]
  We present a state-of-the-art model for fine-grained probability estimation of propositions conditioned on context.<n>We show that our approach consistently outperforms existing fine-tuned and prompting-based methods by a large margin.
  arXiv  Detail & Related papers  (2025-05-02T21:33:18Z)
• A Probabilistic Perspective on Unlearning and Alignment for Large Language Models [48.96686419141881]
  We introduce the first formal probabilistic evaluation framework for Large Language Models (LLMs)<n> Namely, we propose novel metrics with high probability guarantees concerning the output distribution of a model.<n>Our metrics are application-independent and allow practitioners to make more reliable estimates about model capabilities before deployment.
  arXiv  Detail & Related papers  (2024-10-04T15:44:23Z)
• Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs [10.494477811252034]
  Fine-tuning multiplicity can arise in Tabular LLMs on classification tasks.<n>Our work formalizes this unique challenge of fine-tuning multiplicity in Tabular LLMs.<n>We propose a novel measure to quantify consistency of individual predictions without expensive model retraining.
  arXiv  Detail & Related papers  (2024-07-04T22:22:09Z)
• Weak Supervision Performance Evaluation via Partial Identification [46.73061437177238]
  Programmatic Weak Supervision (PWS) enables supervised model training without direct access to ground truth labels. We present a novel method to address this challenge by framing model evaluation as a partial identification problem. Our approach derives reliable bounds on key metrics without requiring labeled data, overcoming core limitations in current weak supervision evaluation techniques.
  arXiv  Detail & Related papers  (2023-12-07T07:15:11Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.