SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.11564 · 2023

Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 12 failures of our instrument; 2 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/2310.11564.json · badge: /api/ran/2310.11564.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
joeljang/rlphf canonical (classifier label)
classifier basis: census
13 ran · 2 no recorded run
FunctionStatusWhere it lives
chars_token_ratio Ran
ran, honoured the contract we drafted
joeljang/rlphf/training/multitask_training.py
pointer only (licence: NONE) · get_code("ec7ad96cced15dae")
How it ran

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

collator Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/training/pmorl.py
pointer only (licence: NONE) · get_code("bda36ad0c44dbd74")
How it ran

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

compute_reward_modeling_metrics Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/gpt4_evaluate/alpaca_farm/reward_modeling_trainer.py
pointer only (licence: NONE) · get_code("cca45bb9a111ab77")
How it ran

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

flatten_dict Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/gpt4_evaluate/alpaca_farm/common.py
pointer only (licence: NONE) · get_code("f5ff77db7757bc92")
How it ran

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

format_output Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/gpt4_evaluate/alpaca_farm/data_preprocessor.py
pointer only (licence: NONE) · get_code("46af3eb303562401")
How it ran

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

format_prompt Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/gpt4_evaluate/alpaca_farm/data_preprocessor.py
pointer only (licence: NONE) · get_code("a71a4bdc37586fe2")
How it ran

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

format_prompt_with_data_frame Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/gpt4_evaluate/alpaca_farm/data_preprocessor.py
pointer only (licence: NONE) · get_code("8b1ea4142642d361")
How it ran

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

generate_prompt Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/generate_rollouts.py
pointer only (licence: NONE) · get_code("dad9dcf30ea1d344")
How it ran

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

generate_prompt_tulu Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/generate_rollouts.py
pointer only (licence: NONE) · get_code("6d93a251945458d6")
How it ran

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

get_reward_stats Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/training/pmorl.py
pointer only (licence: NONE) · get_code("ed46234879c19e1b")
How it ran

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

let_model_save_mem_when_zero_grad Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/gpt4_evaluate/alpaca_farm/common.py
pointer only (licence: NONE) · get_code("9a1871dd5c967ac1")
How it ran

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

prepare_sample_text Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/training/multitask_training.py
pointer only (licence: NONE) · get_code("c91f5610ae8e27c8")
How it ran

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

preprocess_function Ran
ran; our contract draft was wrong, not the code
joeljang/rlphf/training_reward_model.py
pointer only (licence: NONE) · get_code("5240cc5f3702d81a")
How it ran

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

add_preference_prompt_during_val Not yet run
unverified (harvested, no recorded run)
joeljang/rlphf/training/psoups.py
pointer only (licence: NONE) · get_code("fb96ca75dd81e5fc")
How it ran

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

build_dataset Not yet run
unverified (harvested, no recorded run)
joeljang/rlphf/training/pmorl.py
pointer only (licence: NONE) · get_code("fc2e047ee0f8e902")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, joeljang/rlphf 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 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 8 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 7 later) and 7 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
collator 9 other papers
4 dated earlier, 5 later
1909.08593 (2019-09)
Fine-Tuning Language Models from Human Preferences
2204.07705 (2022-04)
SUPER-NATURALINSTRUCTIONS: Generalization via Declarative Instructions on 1600+ NLP Tasks
2304.08177 (2023-04)
Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca
and 6 more not named here
flatten_dict 4 other papers
1 dated earlier, 3 later
2309.09055 (2023-09)
Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF
2402.05133 (2024-02)
Personalized Language Modeling from Personalized Human Feedback
2406.11280 (2024-06)
ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO
and 1 more not named here
compute_reward_modeling_metrics 3 other papers
1 dated earlier, 2 later
2309.09055 (2023-09)
Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF
2402.05133 (2024-02)
Personalized Language Modeling from Personalized Human Feedback
2501.09620 (2025-01)
Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
format_output 3 other papers
1 dated earlier, 2 later
2309.09055 (2023-09)
Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF
2402.05133 (2024-02)
Personalized Language Modeling from Personalized Human Feedback
2501.09620 (2025-01)
Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
format_prompt_with_data_frame 3 other papers
1 dated earlier, 2 later
2309.09055 (2023-09)
Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF
2402.05133 (2024-02)
Personalized Language Modeling from Personalized Human Feedback
2501.09620 (2025-01)
Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
let_model_save_mem_when_zero_grad 3 other papers
1 dated earlier, 2 later
2309.09055 (2023-09)
Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF
2402.05133 (2024-02)
Personalized Language Modeling from Personalized Human Feedback
2501.09620 (2025-01)
Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
format_prompt 2 other papers
2 later
2402.05133 (2024-02)
Personalized Language Modeling from Personalized Human Feedback
2501.09620 (2025-01)
Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
chars_token_ratio 1 other paper
1 dated earlier
2309.16155 (2023-09)
The Trickle-down Impact of Reward (In-)consistency on RLHF

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

While Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with general, aggregate human preferences, it is suboptimal for learning diverse, individual perspectives. In this work, we study Reinforcement Learning from Personalized Human Feedback (RLPHF) problem, wherein LLMs are aligned to multiple (sometimes conflicting) preferences by modeling alignment as a Multi-Objective Reinforcement Learning (MORL) problem. Compared to strong single-objective baselines, we show that we can achieve personalized alignment by decomposing preferences into multiple dimensions. These dimensions are defined based on personalizations that are declared as desirable by the user. In this work, we show that they can be efficiently trained independently in a distributed manner and combined effectively post-hoc through parameter merging. The code is available at https://github.com/joeljang/RLPHF.

For agents

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

get_harvested_code_for_paper("2310.11564")
get_code_for_paper("2310.11564")
have("2310.11564")

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

curl https://syntology.ai/api/ran/2310.11564.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.11564.svg)](https://syntology.ai/paper/2310.11564)

Connect an agent — have() is free.