Papers › HYDRA: Model Factorization Framework for Black-Box LLM Personalization

HYDRA: Model Factorization Framework for Black-Box LLM Personalization

5 Jun 2024arXiv:2406.02888archive 2025-07-28

Yuchen Zhuang, Haotian Sun, Yue Yu, Rushi Qiang, Qifan Wang, Chao Zhang, Bo Dai

Personalization has emerged as a critical research area in modern intelligent systems, focusing on mining users' behavioral history and adapting to their preferences for delivering tailored experiences. Despite the remarkable few-shot capabilities exhibited by black-box large language models (LLMs), the inherent opacity of their model parameters presents significant challenges in aligning the generated output with individual expectations. Existing solutions have primarily focused on prompt design to incorporate user-specific profiles and behaviors; however, such approaches often struggle to generalize effectively due to their inability to capture shared knowledge among all users. To address these challenges, we propose HYDRA, a model factorization framework that captures both user-specific behavior patterns from historical data and shared general knowledge among all users to deliver personalized generation. In order to capture user-specific behavior patterns, we first train a reranker to prioritize the most useful information from top-retrieved relevant historical records. By combining the prioritized history with the corresponding query, we train an adapter to align the output with individual user-specific preferences, eliminating the reliance on access to inherent model parameters of black-box LLMs. Both the reranker and the adapter can be decomposed into a base model with multiple user-specific heads, resembling a hydra. The base model maintains shared knowledge across users, while the multiple personal heads capture user-specific preferences. Experimental results demonstrate that HYDRA outperforms existing state-of-the-art prompt-based methods by an average relative improvement of 9.01% across five diverse personalization tasks in the LaMP benchmark. Our implementation is available at https://github.com/night-chen/HYDRA.

PaperPDFCodeCode 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.

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

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 16 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 12 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 12 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 16 ran (4 with no instrument failure; 12 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 16 samples that ran has no recorded date.

night-chen/hydra officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 16 ran (12 instrument-failed) · 0 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

16 samples harvested: 16 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 12 where Syntology's instrument failed) · 0 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.

12ran · our draft was wrong
4ran

Licence: 16 of the 16 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 night-chen/hydra. “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.

night-chen/hydra official repository 16 samples, 16 ran (12 instrument-failed) · 0 unverified
LongformerForPersonalizedCls adapter/trainer/personalized_trainer.py ran no licence file found · pointer only · da25fbe823b3c54e · report fixture: signature input_ids:Tensor/2/int, attention_mask:Tensor/2/int, global_attention_mask:NoneType/0/?, head_mask:NoneType/0/?, user_mask:Tensor/2/float, token_type_ids:NoneType/0/?, position_ids:NoneType/0/?, inputs_embeds:NoneType/0/?, labels:Tensor/1/int, output_attentions:NoneType/0/?, output_hidden_states:NoneType/0/?, return_dict:bool/0/bool · returned LongformerSequenceClassifierOutput · level recorded 2026-09-24
LongformerPersonalizedClsHead adapter/trainer/personalized_trainer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2b0e9e1de87f7100 · report fixture: returned LongformerPersonalizedClsHead · level recorded 2026-09-22
LongformerSequenceClassifierOutput adapter/trainer/personalized_trainer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8da550fed680318d · report fixture: returned LongformerSequenceClassifierOutput · level recorded 2026-09-22
api_key_list utils/credentials.py ran · our draft was wrong no licence file found · pointer only · 78978cd98b44b675 · report fixture: signature api_group:str/0/str · returned list · level recorded 2026-09-24
extract_after_article prompts/utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 3c022e0b56a5b9aa · report fixture: signature input_string:str/0/str · returned str · level recorded 2026-09-22
extract_after_description prompts/utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 490005de8edac2a7 · report fixture: signature input_string:str/0/str · returned str · level recorded 2026-09-22
extract_numbers in 14 papers metrics/classification_metrics.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 128a6ca41173c482 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-24
extract_strings_between_quotes prompts/utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f11dc768dc0cbefb · report fixture: signature input_string:str/0/str · returned list · level recorded 2026-09-22
get_data in 223 papers utils/util.py ran · our draft was wrong no licence file found · pointer only · 4b094583baf62f2f · report fixture: signature config:dict/0/? · returned Dataset · level recorded 2026-09-24
get_personalize_data utils/util.py ran · our draft was wrong no licence file found · pointer only · 1a267a44dd55b79b · report fixture: signature config:dict/0/? · returned Dataset · level recorded 2026-09-24
load_config in 389 papers utils/util.py ran · our draft was wrong no licence file found · pointer only · 159282975f5b3801 · report fixture: signature config_path:str/0/str · returned dict · level recorded 2026-09-24
mean_pooling in 71 papers prompts/contriever_retriever.py ran · our draft was wrong fingerprinted no licence file found · pointer only · fe0e2df4d9cb5edd · report fixture: signature token_embeddings:Tensor/3/float, mask:Tensor/2/int · returned Tensor · level recorded, date not recorded
postprocess_text in 21 papers metrics/generation_metrics.py ran · our draft was wrong no licence file found · pointer only · 8b51adb8a6c014e5 · report fixture: signature preds:list/1/str, labels:list/1/str · returned tuple · level recorded 2026-09-22
postprocess_text_cls metrics/classification_metrics.py ran no licence file found · pointer only · 33df4a8be7151fcc · report fixture: signature preds:list/1/str, labels:list/1/str · returned tuple · level recorded 2026-09-24
postprocess_text_reg metrics/classification_metrics.py ran · our draft was wrong no licence file found · pointer only · 21eed1ab0d4f98f7 · report fixture: signature preds:list/1/str, labels:list/1/str · returned tuple · level recorded 2026-09-24
prepare_prompts in 11 papers adapter/generate/generate.py ran · our draft was wrong no licence file found · pointer only · a5c4afa103aa6d76 · report fixture: signature prompts:list/1/str, tokenizer:callable/0/?, batch_size:int/0/int · returned list · 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. 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for HYDRA (graph method: HYDRA). 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. LongformerForPersonalizedCls entry · level 1 · ran · da25fbe823b3c54e
  2. LongformerPersonalizedClsHead model · level 1 · ran · 2b0e9e1de87f7100
  3. LongformerSequenceClassifierOutput helper · level 1 · ran · 8da550fed680318d

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="2406.02888") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

General Knowledge

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNAdapterBASEHydra

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