Papers › Local and Global Decoding in Text Generation

Local and Global Decoding in Text Generation

14 Oct 2024arXiv:2410.10810archive 2025-07-28

Daniel Gareev, Thomas Hofmann, Ezhilmathi Krishnasamy, Tiago Pimentel

Text generation, a key component in applications such as dialogue systems, relies on decoding algorithms that sample strings from a language model distribution. Traditional methods, such as top-k and top-π, apply local normalisation to the model's output distribution, which can distort it. In this paper, we investigate the effect of this distortion by introducing globally-normalised versions of these decoding methods. Additionally, we propose an independent Metropolis-Hastings algorithm to approximate sampling from globally-normalised distributions without explicitly computing them. Our empirical analysis compares the performance of local and global normalisation across two decoding algorithms (top-k and top-π) with various hyperparameters, using Pythia language models. Results show that, in most configurations, global decoding performs worse than the local decoding version of the same algorithms -- despite preserving the distribution's integrity. Our results suggest that distortion is an important feature of local decoding algorithms.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2410.10810")

Code

Syntology Ran 11 of 12 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 11 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lowlypalace/global-decoding officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 11 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

11ran
1unverified

Licence: 12 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from lowlypalace/global-decoding. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

calculate_context_length lowlypalace/global-decoding/src/experiments/helpers.py official repository ran no licence file found · pointer only · 8cdfeccd65fcf064 · report
compute_95ci lowlypalace/global-decoding/src/results/get_results.py official repository ran fingerprinted no licence file found · pointer only · 2739ee7e7e37880c · report
compute_kde lowlypalace/global-decoding/src/mcmc/plots.py official repository ran no licence file found · pointer only · 9376ebd2fbbb675d · report
filter_padding_tokens lowlypalace/global-decoding/src/results/get_results.py official repository ran fingerprinted no licence file found · pointer only · 1f446017f9ed893c · report
indicator_top_k lowlypalace/global-decoding/src/experiments/global_decoding.py official repository ran fingerprinted no licence file found · pointer only · 74f767a079f7fb9a · report
load_json_file lowlypalace/global-decoding/src/results/get_results.py official repository ran no licence file found · pointer only · b4716300a32ace4a · report
metropolis_hastings lowlypalace/global-decoding/src/mcmc/metropolis_hastings.py official repository ran no licence file found · pointer only · 9ad02553048ba5c5 · report
normalization_constant lowlypalace/global-decoding/src/experiments/local_decoding.py official repository ran no licence file found · pointer only · 8b81b2e202edcee5 · report
predict_logits lowlypalace/global-decoding/src/experiments/helpers.py official repository ran no licence file found · pointer only · b45a8da2e2ea7e5b · report
replace_nan_ci lowlypalace/global-decoding/src/results/plots.py official repository ran no licence file found · pointer only · 1c1380cdab9cb649 · report
top_k_filtering lowlypalace/global-decoding/src/experiments/helpers.py official repository ran no licence file found · pointer only · 7939c932cc2ff354 · report
generate_sequences_util lowlypalace/global-decoding/src/sequences/generate_sequences_util.py official repository unverified no licence file found · pointer only · 6a9447860dbc0e1e · report

Tasks

Language ModelingLanguage ModellingText Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Pythia

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections