SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.15313 · ICLR · 2025

Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models

Philip Torr, Mohamed Elhoseiny, Adel Bibi, Wenxuan Zhang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 2 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2408.15313.json · badge: /api/ran/2408.15313.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
wx-zhang/bfpo canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
add_dataset_name Ran
ran; our contract draft was wrong, not the code
wx-zhang/bfpo/src/alignment/data.py
pointer only (licence: NONE) · get_code("4c7a20efd8b515fe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wx-zhang/bfpo 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.

apply_chat_template Ran
ran; our contract draft was wrong, not the code
wx-zhang/bfpo/src/alignment/data.py
pointer only (licence: NONE) · get_code("ecf650a71ce5efc6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wx-zhang/bfpo 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_quantization_config Not yet run
unverified (harvested, no recorded run)
wx-zhang/bfpo/src/alignment/model_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from tengxiao1/GSIL, is pointer only (licence: NONE) · get_code("c9ed692d311c459a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wx-zhang/bfpo 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
get_quantization_config 1 other paper
1 later
2410.10093 (2024-10)
How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Fine-tuning large language models (LLMs) on human preferences, typically through reinforcement learning from human feedback (RLHF), has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during fine-tuning remains a critical concern, and mitigating the potential conflicts in safety and helpfulness is costly in RLHF. To address this issue, we propose a supervised learning framework called Bi-Factorial Preference Optimization (BFPO), which re-parameterizes a joint RLHF objective of both safety and helpfulness into a single supervised learning objective. In supervised optimization, a labeling function is used to capture the global preferences ranking to balance both safety and helpfulness. To evaluate BFPO, we develop a benchmark that includes comprehensive discriminative and generative tasks for helpfulness and harmlessness. The results indicate that our method significantly outperforms existing approaches in both safety and helpfulness. Moreover, BFPO achieves the same level of safety as methods that heavily rely on human labor with less than 10% of the computational resources and human prompting and annotation process. The training recipes can be found here: https://github.com/wx-zhang/bfpo. Warning: This paper contains offensive or harmful content.

For agents

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

get_harvested_code_for_paper("2408.15313")
get_code_for_paper("2408.15313")
have("2408.15313")

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

curl https://syntology.ai/api/ran/2408.15313.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.15313.svg)](https://syntology.ai/paper/2408.15313)

Connect an agent — have() is free.