Papers › TIES-Merging: Resolving Interference When Merging Models

TIES-Merging: Resolving Interference When Merging Models

2 Jun 2023NeurIPS 2023 11arXiv:2306.01708archive 2025-07-28

Prateek Yadav, Derek Tam, Leshem Choshen, Colin Raffel, Mohit Bansal

Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have led to a proliferation of task-specific fine-tuned models, which typically can only perform a single task and do not benefit from one another. Recently, model merging techniques have emerged as a solution to combine multiple task-specific models into a single multitask model without performing additional training. However, existing merging methods often ignore the interference between parameters of different models, resulting in large performance drops when merging multiple models. In this paper, we demonstrate that prior merging techniques inadvertently lose valuable information due to two major sources of interference: (a) interference due to redundant parameter values and (b) disagreement on the sign of a given parameter's values across models. To address this, we propose our method, TRIM, ELECT SIGN & MERGE (TIES-Merging), which introduces three novel steps when merging models: (1) resetting parameters that only changed a small amount during fine-tuning, (2) resolving sign conflicts, and (3) merging only the parameters that are in alignment with the final agreed-upon sign. We find that TIES-Merging outperforms several existing methods in diverse settings covering a range of modalities, domains, number of tasks, model sizes, architectures, and fine-tuning settings. We further analyze the impact of different types of interference on model parameters, and highlight the importance of resolving sign interference. Our code is available at https://github.com/prateeky2806/ties-merging

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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.

Syntology holds a reference implementation of TIES-MERGING, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='TIES-MERGING') (how to connect); the free check have('2306.01708') needs no token.

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

Code

Syntology 8 code samples: 7 from 3 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 8: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 6 samples from 2 repositories, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 4 samples that ran has no recorded date.

prateeky2806/ties-merging officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
EnnengYang/AdaMerging mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
flowritecom/flow-merge mentioned on GitHubpytorchSyntology: 4 samples, 0 ran · 4 unverified report
yanyang19/ImPart mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Editing Models with Task Arithmetic (arXiv:2212.04089; that paper's own run record: 5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified) and ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and... (arXiv:2504.13237; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

8 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
3ran; the contract check could not run
4unverified

Licence: 1 of the 8 samples is 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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.

prateeky2806/ties-merging official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
resolve_lambda_code src/ties_merging.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted BSD-3-Clause (permissive) · adff87f187a088be · report fixture: signature lambda_code:tuple/1/float · returned Tensor · level recorded, date not recorded
EnnengYang/AdaMerging community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
disjoint_merge src/ties_merging_utils.py ran · our draft was wrong MIT (permissive) · d2a53ee4479956ae · report fixture: signature Tensor:Tensor/2/float, merge_func:str/0/str, sign_to_mult:Tensor/1/float · returned Tensor · level recorded 2026-09-22
ties_merging in 6 papers src/ties_merging_utils.py ran; the contract check could not run (RAISES) MIT (permissive) · 7b834a39961b956a · report fixture: signature flat_task_checks:Tensor/2/float, reset_thresh:float/0/float, merge_func:str/0/str · returned Tensor · level recorded 2026-09-22
flowritecom/flow-merge community (archive-listed) 4 samples, 0 ran · 4 unverified
BaseMergeMethodSettings flow_merge/lib/merge_methods/task_arithmetic.py unverified Apache-2.0 (permissive) · 27c058dc73f0bc72 · report
Model in 227 papers flow_merge/lib/merge_methods/task_arithmetic.py unverified Apache-2.0 (permissive) · 07b31b99cc6756ae · report
TaskArithmeticSettings flow_merge/lib/merge_methods/task_arithmetic.py unverified Apache-2.0 (permissive) · 13ed3abc8bafa589 · report
TiesMergingSettings flow_merge/lib/merge_methods/task_arithmetic.py unverified Apache-2.0 (permissive) · e5f70e4892a42b45 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
topk_values_mask in 7 papers repository not located ran; the contract check could not run (RAISES) · metamorphic tier: deterministic licence of this copy not recorded · 225c26ebc567caaa · report fixture: signature M:Tensor/2/float, K:float/0/float, return_mask:bool/0/bool · returned tuple · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

3 assemblies on this paper: 2 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for TIES-MERGING (graph method: TIES-MERGING), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. ties_merging entry · level 2 · ran · honoured contract · 66f89cfa3fbf8010f5bcd5ba8186110f8bfde17335ac8e1e0460c13945555487

2 sibling assemblies for TIES-MERGING (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for TIES-MERGING (graph method: TIES-MERGING). 5 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. ties_merging entry · level 1 · ran; the contract check could not run (RAISES) · 7b834a39961b956a
  2. disjoint_merge helper · level 1 · ran · our draft was wrong · d2a53ee4479956ae
  3. resolve_sign helper · level 1 · ran · honoured contract · 843a0f021c3f85d2
  4. topk_values_mask helper · level 1 · ran; the contract check could not run (RAISES) · 225c26ebc567caaa
  5. resolve_zero_signs helper · level 1 · ran; the contract check could not run · 860408c2bd01950e

harvested Assembly for TIES-MERGING (graph method: TIES-MERGING). 4 bricks; individually on a fixture: 0 ran · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. TiesMergingSettings entry · level 0 · unverified · e5f70e4892a42b45
  2. Model helper · level 0 · unverified · 07b31b99cc6756ae
  3. TaskArithmeticSettings helper · level 0 · unverified · 13ed3abc8bafa589
  4. BaseMergeMethodSettings helper · level 0 · unverified · 27c058dc73f0bc72

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2306.01708") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Transfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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