Verbalized Particle Posterior: Bayesian Inference over Natural Language Hypotheses

• URL: http://arxiv.org/abs/2607.22961v1
• Date: Sat, 25 Jul 2026 00:04:56 GMT
• Title: Verbalized Particle Posterior: Bayesian Inference over Natural Language Hypotheses
• Abstract summary: Verbalized Machine Learning (VML) parameterizes a model as a natural-language prompt that an LLM evaluates as f(x; theta)<n>We propose the Verbalized Particle Posterior (VPP), which treats verbalized learning as a Bayesian inference problem.
• Score: 8.864909622103388
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Verbalized Machine Learning (VML) parameterizes a model as a natural-language prompt that an LLM evaluates as f(x; theta). The framework is interpretable, but it commits to a single hypothesis with no measure of uncertainty, and that hypothesis varies substantially across optimization runs on the same data. We propose the Verbalized Particle Posterior (VPP), which treats verbalized learning as a Bayesian inference problem: maintain a population of natural-language hypotheses as particles, update them with Metropolis-Hastings (VPP-MH) or Sequential Monte Carlo (VPP-SMC), and predict by Bayesian model averaging. Both algorithms treat the LLM as a black box, requiring no access to logits or gradients. A distinctive consequence follows. In classical Bayesian learning, model selection sits outside the posterior; in VPP both model structure and parameters share a single language space, and the posterior ranges over both. We evaluate VPP on regression, classification, and rule-discovery benchmarks. It improves over a single VML run on every benchmark and matches or exceeds an oracle-best ensemble of independent VML runs on most, while eliminating the catastrophic single-run failures that VML occasionally produces. Because each particle is a human-readable hypothesis, the posterior is itself something a reader can inspect, seeing in plain text which explanations the data supported and which it ruled out.

Related papers

• Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models [45.42736932931535]
  Law of total probability asserts that prior-weighted conditional distributions aggregate into population-level marginals over any valid partition of the population.<n>We use binary trees as an evaluation scaffold to partition a population into increasingly fine-grained subpopulations.<n>We prompt LLMs with verbalized subpopulation descriptions in context, aggregate the resulting estimates back into population-level estimates, and compare them across partitions of varying granularity.
  arXiv  Detail & Related papers  (2026-07-16T17:59:31Z)
• Hypothesis generation and updating in large language models [0.0]
  Large language models (LLMs) increasingly help people solve problems, but how they perform inference remains unclear.<n>We study this question in the number game, a controlled setting in which a learner infers the hypothesis supported by a few positive integers.<n>We measure the posterior over hypotheses using three complementary probes: posterior prediction, hypothesis evaluation, and hypothesis generation.
  arXiv  Detail & Related papers  (2026-05-07T08:24:54Z)
• How Large Language Models Get Stuck: Early structure with persistent errors [0.0]
  We trained Meta's OPT model on the 100M word BabyLM dataset.<n>We evaluated it on the BLiMP benchmark, which consists of 67 classes.<n>We tested the model's preference for grammatical over ungrammatical sentences.
  arXiv  Detail & Related papers  (2026-02-27T22:49:11Z)
• Leveraging Large Language Models for Predictive Analysis of Human Misery [1.2458057399345226]
  This study investigates the use of Large Language Models (LLMs) for predicting human-perceived misery scores.<n>We evaluate multiple prompting strategies, including zero-shot, fixed-context few-shot, and retrieval-based prompting.<n>To move beyond static evaluation, we introduce the "Misery Game Show", a novel gamified framework inspired by a television format.
  arXiv  Detail & Related papers  (2025-08-18T07:02:59Z)
• Verbalized Machine Learning: Revisiting Machine Learning with Language Models [63.10391314749408]
  We introduce the framework of verbalized machine learning (VML)<n>VML constrains the parameter space to be human-interpretable natural language.<n>We empirically verify the effectiveness of VML, and hope that VML can serve as a stepping stone to stronger interpretability.
  arXiv  Detail & Related papers  (2024-06-06T17:59:56Z)
• Paloma: A Benchmark for Evaluating Language Model Fit [112.481957296585]
  Evaluations of language models (LMs) commonly report perplexity on monolithic data held out from training.<n>We introduce Perplexity Analysis for Language Model Assessment (Paloma), a benchmark to measure LM fit to 546 English and code domains.
  arXiv  Detail & Related papers  (2023-12-16T19:12:45Z)
• Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment [82.60594940370919]
  We propose the FlipFlop experiment to study the multi-turn behavior of Large Language Models (LLMs) We show that models flip their answers on average 46% of the time and that all models see a deterioration of accuracy between their first and final prediction, with an average drop of 17% (the FlipFlop effect) We conduct finetuning experiments on an open-source LLM and find that finetuning on synthetically created data can mitigate - reducing performance deterioration by 60% - but not resolve sycophantic behavior entirely.
  arXiv  Detail & Related papers  (2023-11-14T23:40:22Z)
• Conformal Language Modeling [61.94417935386489]
  We propose a novel approach to conformal prediction for generative language models (LMs) Standard conformal prediction produces prediction sets with rigorous, statistical guarantees. We demonstrate the promise of our approach on multiple tasks in open-domain question answering, text summarization, and radiology report generation.
  arXiv  Detail & Related papers  (2023-06-16T21:55:08Z)
• Understanding Emergent In-Context Learning from a Kernel Regression Perspective [55.95455089638838]
  Large language models (LLMs) have initiated a paradigm shift in transfer learning.<n>This paper proposes a kernel-regression perspective of understanding LLMs' ICL bahaviors when faced with in-context examples.<n>We find that during ICL, the attention and hidden features in LLMs match the behaviors of a kernel regression.
  arXiv  Detail & Related papers  (2023-05-22T06:45:02Z)
• Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling [95.9542389945259]
  Sentence scoring aims at measuring the likelihood of a sentence and is widely used in many natural language processing scenarios. We propose textitTranscormer -- a Transformer model with a novel textitsliding language modeling (SLM) for sentence scoring.
  arXiv  Detail & Related papers  (2022-05-25T18:00:09Z)
• Query Training: Learning a Worse Model to Infer Better Marginals in Undirected Graphical Models with Hidden Variables [11.985433487639403]
  Probabilistic graphical models (PGMs) provide a compact representation of knowledge that can be queried in a flexible way. We introduce query training (QT), a mechanism to learn a PGM that is optimized for the approximate inference algorithm that will be paired with it. We demonstrate experimentally that QT can be used to learn a challenging 8-connected grid Markov random field with hidden variables.
  arXiv  Detail & Related papers  (2020-06-11T20:34:32Z)

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.