Eliciting Numerical Predictive Distributions of LLMs Without Autoregression

• URL: http://arxiv.org/abs/2603.02913v1
• Date: Tue, 03 Mar 2026 12:13:40 GMT
• Title: Eliciting Numerical Predictive Distributions of LLMs Without Autoregression
• Abstract summary: We study whether distributional properties of LLM predictions can be recovered without explicit autoregressive generation.<n>Our results suggest that LLM embeddings carry informative signals about summary statistics of their predictive distributions.
• Score: 46.67044415202221
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have recently been successfully applied to regression tasks -- such as time series forecasting and tabular prediction -- by leveraging their in-context learning abilities. However, their autoregressive decoding process may be ill-suited to continuous-valued outputs, where obtaining predictive distributions over numerical targets requires repeated sampling, leading to high computational cost and inference time. In this work, we investigate whether distributional properties of LLM predictions can be recovered without explicit autoregressive generation. To this end, we study a set of regression probes trained to predict statistical functionals (e.g., mean, median, quantiles) of the LLM's numerical output distribution directly from its internal representations. Our results suggest that LLM embeddings carry informative signals about summary statistics of their predictive distributions, including the numerical uncertainty. This investigation opens up new questions about how LLMs internally encode uncertainty in numerical tasks, and about the feasibility of lightweight alternatives to sampling-based approaches for uncertainty-aware numerical predictions.

Related papers

• LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications [76.41731220830714]
  Large language models (LLMs) now support forecasting systems that combine language-based reasoning with temporal data, evidence retrieval, external tools, and iterative prediction.<n>We examine applications in finance, weather, health, energy, and operations, and we summarize the benchmarks and datasets used for evaluation.
  arXiv  Detail & Related papers  (2026-08-24T10:02:39Z)
• Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language [15.221434185896541]
  We evaluate whether nine LLMs meet requirements within a two-stage prediction pipeline.<n>We simulate predictions from an upstream model by taking samples from a Beta distribution parameterized by its mode and prior sample size.<n>We find that LLMs are generally consistent but miscalibrated, with substantially weaker performance on uncertainty than on likelihood tasks.
  arXiv  Detail & Related papers  (2026-07-04T13:57:21Z)
• How Well Do LLMs Predict Human Behavior? A Measure of their Pretrained Knowledge [0.0]
  Large language models (LLMs) are increasingly used to predict human behavior.<n>We propose a measure for evaluating how much knowledge a pretrained LLM brings to such a prediction.<n>We estimate this measure by comparing the prediction error of a fixed LLM in a given domain to that of flexible machine learning models trained on increasing samples of domain-specific data.
  arXiv  Detail & Related papers  (2026-01-18T10:28:54Z)
• Predicting Language Models' Success at Zero-Shot Probabilistic Prediction [23.802154124780376]
  We investigate the capabilities of large language models (LLMs) as zero-shot models for generating individual-level characteristics.<n>We find that LLMs' performance is highly variable, both on tasks within the same dataset and across different datasets.<n>We construct metrics to predict LLMs' performance at the task level, aiming to distinguish between tasks where LLMs may perform well and where they are likely unsuitable.
  arXiv  Detail & Related papers  (2025-09-18T18:57:05Z)
• Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs [57.82819770709032]
  Large language models (LLMs) can be effective context-aided forecasters via na"ive direct prompting.<n>ReDP improves interpretability by eliciting explicit reasoning traces, allowing us to assess the model's reasoning over the context.<n>CorDP leverages LLMs solely to refine existing forecasts with context, enhancing their applicability in real-world forecasting pipelines.<n> IC-DP proposes embedding historical examples of context-aided forecasting tasks in the prompt, substantially improving accuracy even for the largest models.
  arXiv  Detail & Related papers  (2025-08-13T16:02:55Z)
• Scaling Laws for Predicting Downstream Performance in LLMs [75.28559015477137]
  This work focuses on the pre-training loss as a more computation-efficient metric for performance estimation.<n>We present FLP-M, a fundamental approach for performance prediction that addresses the practical need to integrate datasets from multiple sources during pre-training.
  arXiv  Detail & Related papers  (2024-10-11T04:57:48Z)
• 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)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language [35.84181171987974]
  Our goal is to build a regression model that can process numerical data and make probabilistic predictions at arbitrary locations.<n>We start by exploring strategies for eliciting explicit, coherent numerical predictive distributions from Large Language Models.<n>We demonstrate the ability to usefully incorporate text into numerical predictions, improving predictive performance and giving quantitative structure that reflects qualitative descriptions.
  arXiv  Detail & Related papers  (2024-05-21T15:13:12Z)
• Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation [73.58618024960968]
  An increasing number of studies are employing large language models (LLMs) as agents to emulate the sequential decision-making processes of humans.<n>This arouses curiosity regarding the capacity of LLM agents to comprehend probability distributions.<n>Our analysis indicates that LLM agents can understand probabilities, but they struggle with probability sampling.
  arXiv  Detail & Related papers  (2024-04-13T16:59:28Z)
• 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)
• Efficient Estimation and Evaluation of Prediction Rules in Semi-Supervised Settings under Stratified Sampling [6.930951733450623]
  We propose a two-step semi-supervised learning (SSL) procedure for evaluating a prediction rule derived from a working binary regression model. In step I, we impute the missing labels via weighted regression with nonlinear basis functions to account for nonrandom sampling. In step II, we augment the initial imputations to ensure the consistency of the resulting estimators.
  arXiv  Detail & Related papers  (2020-10-19T12:54:45Z)

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.