SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.11531 · 2024

Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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; 6 failures of our instrument; 4 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/2404.11531.json · badge: /api/ran/2404.11531.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
cmavro/packllm canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
format_dataset Ran
ran; our contract draft was wrong, not the code
cmavro/packllm/downstream_tasks/get_task.py
pointer only (licence: NONE) · get_code("82fab1f6e6bddec2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cmavro/packllm 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.

mean_pooling Ran
ran; our contract draft was wrong, not the code
cmavro/packllm/downstream_tasks/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from dengyang17/llm-proactive, is pointer only (licence: NONE) · get_code("77f69af078e09830")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cmavro/packllm 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.

prepro_sentence_pair Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cmavro/packllm/downstream_tasks/icl_data.py
pointer only (licence: NONE) · get_code("faa9fbf7cc4e66c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cmavro/packllm 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.

prepro_sentence_pair_single Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cmavro/packllm/downstream_tasks/icl_data.py
pointer only (licence: NONE) · get_code("1f230cbd5842e2ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cmavro/packllm 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.

process_mmlu_examples Ran
ran; our contract draft was wrong, not the code
cmavro/packllm/downstream_tasks/get_task.py
pointer only (licence: NONE) · get_code("99a5947cc60a3cb3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cmavro/packllm 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.

process_openbookqa_examples Ran
ran; our contract draft was wrong, not the code
cmavro/packllm/downstream_tasks/get_task.py
pointer only (licence: NONE) · get_code("dc07ce32fc4a428a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cmavro/packllm 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.

calculate_sentence_transformer_embedding Not yet run
unverified (harvested, no recorded run)
cmavro/packllm/downstream_tasks/utils.py
pointer only (licence: NONE) · get_code("c0016ed0e6b96ff4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cmavro/packllm 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.

calculate_sentence_transformer_embedding_m Not yet run
unverified (harvested, no recorded run)
cmavro/packllm/downstream_tasks/utils.py
pointer only (licence: NONE) · get_code("ce4a54944b0f471c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cmavro/packllm 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.

get_instance_length Not yet run
unverified (harvested, no recorded run)
cmavro/packllm/downstream_tasks/prompt_retrieval.py
pointer only (licence: NONE) · get_code("ddf793183ffe3659")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cmavro/packllm 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.

setup_fp16 Not yet run
unverified (harvested, no recorded run)
cmavro/packllm/downstream_tasks/icl_model.py
pointer only (licence: NONE) · get_code("cbf1d84d85c303cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cmavro/packllm 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 1 later) and 5 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
mean_pooling 22 other papers
11 dated earlier, 3 the same month, 8 later · 1 only as an assembly brick
2206.04624 (2022-06)
Factuality Enhanced Language Models for Open-Ended Text Generation
2023.findings-emnlp.540 (2023 (year only))
Open-ended Commonsense Reasoning with Unrestricted Answer Scope
2302.05698 (2023-02)
Compositional Exemplars for In-context Learning
and 19 more not named here
format_dataset 2 other papers
2 dated earlier
2212.09741 (2022-12)
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
2310.20046 (2023-10)
Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection
get_instance_length 2 other papers
2 dated earlier
2310.10873 (2023-10)
IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
2310.20046 (2023-10)
Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection
prepro_sentence_pair 1 other paper
1 dated earlier
2310.20046 (2023-10)
Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection
setup_fp16 1 other paper
1 dated earlier
2310.20046 (2023-10)
Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection

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

Fusing knowledge from multiple Large Language Models (LLMs) can combine their diverse strengths to achieve improved performance on a given task. However, current fusion approaches either rely on learning-based fusers that do not generalize to new LLMs, or do not take into account how well each LLM understands the input. In this work, we study LLM fusion at test-time, which enables leveraging knowledge from arbitrary user-specified LLMs during inference. We introduce Pack of LLMs (PackLLM), an effective method for test-time fusion that leverages each LLM's expertise, given an input prompt. PackLLM performs model fusion by solving an optimization problem for determining each LLM's importance, so that perplexity over the input prompt is minimized. First, our simple PackLLM-sim variant validates that perplexity is a good indicator for measuring each LLM's expertise. Second, our PackLLM-opt variant approximately solves the perplexity minimization problem via a greedy algorithm. The derived importance weights are used to combine the LLMs during inference. We conduct experiments with over 100 total LLMs on a diverse set of tasks. Experimental results show that (i) perplexity is a reliable measure for LLM fusion, (ii) PackLLM outperforms test-time fusion baselines by 1.89% accuracy points, and (iii) PackLLM can leverage new LLMs to improve performance over learning-based fusion approaches by 3.92-11.94% accuracy points.

For agents

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

get_harvested_code_for_paper("2404.11531")
get_code_for_paper("2404.11531")
have("2404.11531")

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

curl https://syntology.ai/api/ran/2404.11531.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.11531.svg)](https://syntology.ai/paper/2404.11531)

Connect an agent — have() is free.