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

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

17 Apr 2024arXiv:2404.11531archive 2025-07-28

Costas Mavromatis, Petros Karypis, George Karypis

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 6 ran (1 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

cmavro/packllm officialmentioned in paperpytorchSyntology: 10 samples, 6 ran (5 instrument-failed) · 4 unverified 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

10 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
1ran; the contract check could not run
1ran
4unverified

Licence: 10 of the 10 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 cmavro/packllm. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

cmavro/packllm official repository 10 samples, 6 ran (5 instrument-failed) · 4 unverified
format_dataset in 5 papers downstream_tasks/get_task.py ran · our draft was wrong no licence file found · pointer only · 82fab1f6e6bddec2 · report fixture: signature sample:dict/0/? · returned dict · level recorded 2026-09-24
mean_pooling in 71 papers downstream_tasks/utils.py ran · our draft was wrong no licence file found · pointer only · 77f69af078e09830 · report fixture: signature model_output:tuple/1/Tensor, attention_mask:Tensor/2/float · returned Tensor · level recorded, date not recorded
prepro_sentence_pair downstream_tasks/icl_data.py ran; the contract check could not run (RAISES) no licence file found · pointer only · faa9fbf7cc4e66c1 · report fixture: signature train_inputs:list/1/list, test_inputs:list/1/list, max_length:int/0/int, bos_token_id:int/0/int, eos_token_id:int/0/int, allow_truncation:bool/0/bool · returned dict · level recorded 2026-09-24
prepro_sentence_pair_single downstream_tasks/icl_data.py ran no licence file found · pointer only · 1f230cbd5842e2ab · report fixture: signature ids1:list/1/int, ids2:list/1/int, max_length:int/0/int, bos_token_id:int/0/int, eos_token_id:int/0/int, allow_truncation:bool/0/bool · returned tuple · level recorded 2026-09-24
process_mmlu_examples downstream_tasks/get_task.py ran · our draft was wrong no licence file found · pointer only · 99a5947cc60a3cb3 · report fixture: signature examples:list/1/dict · returned list · level recorded 2026-09-24
process_openbookqa_examples downstream_tasks/get_task.py ran · our draft was wrong no licence file found · pointer only · dc07ce32fc4a428a · report fixture: signature examples:list/1/dict · returned list · level recorded 2026-09-24
calculate_sentence_transformer_embedding downstream_tasks/utils.py unverified no licence file found · pointer only · c0016ed0e6b96ff4 · report
calculate_sentence_transformer_embedding_m downstream_tasks/utils.py unverified no licence file found · pointer only · ce4a54944b0f471c · report
get_instance_length downstream_tasks/prompt_retrieval.py unverified no licence file found · pointer only · ddf793183ffe3659 · report
setup_fp16 downstream_tasks/icl_model.py unverified no licence file found · pointer only · cbf1d84d85c303cc · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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