MétaCan
Menu
Back to cohort

Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce

2025· article· W4416036024 on OpenAlexfundno aff
Haojin Wang, Zining Zhu, Freda Shi

Bibliographic record

Venuenot available
Typearticle
Language
FieldSocial Sciences
TopicLanguage and cultural evolution
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of CanadaCanadian Institute for Advanced Research
KeywordsExpressivityDistribution (mathematics)Language modelStatistical modelGamma distributionProbability distribution

Abstract

fetched live from OpenAlex

Autoregressive neural language models (LMs) generate a probability distribution over tokens at each time step given a prompt.In this work, we attempt to systematically understand the probability distributions that LMs can produce, showing that some distributions are significantly harder to elicit than others.Specifically, for any target next-token distribution over the vocabulary, we attempt to find a prompt that induces the LM to output a distribution as close as possible to the target, using either soft (Li and Liang, 2021) or hard (Wallace et al., 2019) gradient-based prompt tuning.We find that (1) in general, distributions with very low or very high entropy are easier to approximate than those with moderate entropy; (2) among distributions with the same entropy, those containing "outlier tokens" are easier to approximate; (3) target distributions generated by LMs-even LMs with different tokenizers-are easier to approximate than randomly chosen targets.These results offer insights into the expressiveness of LMs and the challenges of using them as probability distribution proposers.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.035
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.005
Threshold uncertainty score0.025

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0050.035
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.000
Science and technology studies0.0000.002
Scholarly communication0.0020.006
Open science0.0010.001
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0040.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.067
GPT teacher head0.319
Teacher spread0.252 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicLanguage and cultural evolutionFrench-language works237,207