SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.06925 · EMNLP · 2024

A Thorough Examination of Decoding Methods in the Era of LLMs

Deng Cai, Yujiu Yang, Wai Lam, Yifan Wang, Zhisong Zhang, Chufan Shi, Haoran Yang

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.06925.json · badge: /api/ran/2402.06925.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
davidfanzz/llm_decoding canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
estimate_s Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
davidfanzz/llm_decoding/fsd/utils.py
pointer only (licence: NONE) · get_code("955f489f3947a84d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, davidfanzz/llm_decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

strip_string Ran
ran; our contract draft was wrong, not the code
davidfanzz/llm_decoding/lm_eval/tasks/gsm8k.py
pointer only (licence: NONE); the stored copy get_code serves, from ChengpengLi1003/CoRT, is pointer only (licence: NONE) · get_code("06b04cb075356fb9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, davidfanzz/llm_decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

topk_logits_filter Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
davidfanzz/llm_decoding/fsd/utils.py
pointer only (licence: NONE) · get_code("746acb2f1047992f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, davidfanzz/llm_decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

topp_logits_filter Ran
ran; our contract draft was wrong, not the code
davidfanzz/llm_decoding/fsd/utils.py
pointer only (licence: NONE) · get_code("710becce1c5418f5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, davidfanzz/llm_decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_answer Not yet run
unverified (harvested, no recorded run)
davidfanzz/llm_decoding/lm_eval/tasks/gsm8k.py
pointer only (licence: NONE) · get_code("ac208e27f559cfcb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, davidfanzz/llm_decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

extract_between_chars Not yet run
unverified (harvested, no recorded run)
davidfanzz/llm_decoding/lm_eval/tasks/human_eval.py
pointer only (licence: NONE) · get_code("e3576c3454a156ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, davidfanzz/llm_decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

run_pylint Not yet run
unverified (harvested, no recorded run)
davidfanzz/llm_decoding/lm_eval/tasks/human_eval.py
pointer only (licence: NONE) · get_code("58de27a7d6e8a0c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, davidfanzz/llm_decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
strip_string 4 other papers
1 dated earlier, 3 later
2309.17452 (2023-09)
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
2410.15700 (2024-10)
InternLM2.5-StepProver: Advancing Automated Theorem Proving via Critic-Guided Search
2502.06781 (2025-02)
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current era of general-purpose large language models (LLMs). Moreover, the recent influx of decoding strategies has further complicated this landscape. This paper provides a comprehensive and multifaceted analysis of various decoding methods within the context of LLMs, evaluating their performance, robustness to hyperparameter changes, and decoding speeds across a wide range of tasks, models, and deployment environments. Our findings reveal that decoding method performance is notably task-dependent and influenced by factors such as alignment, model size, and quantization. Intriguingly, sensitivity analysis exposes that certain methods achieve superior performance at the cost of extensive hyperparameter tuning, highlighting the trade-off between attaining optimal results and the practicality of implementation in varying contexts.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.06925")
get_code_for_paper("2402.06925")
have("2402.06925")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.06925.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.06925.svg)](https://syntology.ai/paper/2402.06925)

Connect an agent — have() is free.