SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.04556 · 2024

BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

12 of 13 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, 4 violated it and 0 have no contract verdict; 8 failures of our instrument; 1 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2408.04556.json · badge: /api/ran/2408.04556.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
cyp-jlu-ai/ba-lora canonical (classifier label)
classifier basis: census
12 ran · 1 no recorded run
FunctionStatusWhere it lives
is_number Ran
ran, violated the contract we drafted
cyp-jlu-ai/ba-lora/inference/gsm8k_inference.py
pointer only (licence: NONE) · get_code("0fe9cf6c00ef56ea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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.

batch_data Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cyp-jlu-ai/ba-lora/inference/gsm8k_inference.py
pointer only (licence: NONE) · get_code("5c20985938875f5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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_one_completion Ran
ran; our contract draft was wrong, not the code
cyp-jlu-ai/ba-lora/inference/humaneval.py
pointer only (licence: NONE) · get_code("dccdc98b10215ab7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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.

is_digit Ran
ran, violated the contract we drafted
cyp-jlu-ai/ba-lora/inference/grader.py
pointer only (licence: NONE) · get_code("8ae8c583b21633b3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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.

last_boxed_only Ran
ran; our contract draft was wrong, not the code
cyp-jlu-ai/ba-lora/inference/util.py
pointer only (licence: NONE); the stored copy get_code serves, from Rambo-Yi/TLora, is pointer only (licence: NONE) · get_code("8720975b15d076e8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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.

last_boxed_only_string Ran
ran; our contract draft was wrong, not the code
cyp-jlu-ai/ba-lora/inference/util.py
pointer only (licence: NONE) · get_code("0b14c648516c38a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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.

load_data Ran
ran; our contract draft was wrong, not the code
cyp-jlu-ai/ba-lora/tsne_visualization.py
pointer only (licence: NONE) · get_code("5c29924486e3c3e2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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.

math_equal Ran
ran, violated the contract we drafted
cyp-jlu-ai/ba-lora/inference/grader.py
pointer only (licence: NONE) · get_code("65c738adb08e913c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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.

math_equal_process Ran
ran, violated the contract we drafted
cyp-jlu-ai/ba-lora/inference/grader.py
pointer only (licence: NONE) · get_code("f63c83de2a26f67c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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.

only_until_first_boxed_from_tokens Ran
ran; our contract draft was wrong, not the code
cyp-jlu-ai/ba-lora/inference/util.py
pointer only (licence: NONE); the stored copy get_code serves, from Rambo-Yi/TLora, is pointer only (licence: NONE) · get_code("0bbf876ced018c83")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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.

post_process Ran
ran; our contract draft was wrong, not the code
cyp-jlu-ai/ba-lora/inference/humaneval.py
pointer only (licence: NONE); the stored copy get_code serves, from rainstonee/CDKA, is pointer only (licence: NONE) · get_code("48720117c27620bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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.

remove_boxed Ran
ran; our contract draft was wrong, not the code
cyp-jlu-ai/ba-lora/inference/math_inference.py
pointer only (licence: NONE) · get_code("f3bbe264b05aadd3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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.

perform_tsne Not yet run
unverified (harvested, no recorded run)
cyp-jlu-ai/ba-lora/tsne_visualization.py
pointer only (licence: NONE) · get_code("1d2acce665f00dcc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cyp-jlu-ai/ba-lora 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 1 the same month, 6 later) and 4 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
remove_boxed 20 other papers
11 dated earlier, 8 later, 1 same year, order not determinable · 1 only as an assembly brick
2103.03874 (2021-03)
Measuring Mathematical Problem Solving With the MATH Dataset
2309.06275 (2023-09)
Re-Reading Improves Reasoning in Large Language Models
2309.12284 (2023-09)
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
and 17 more not named here
is_number 18 other papers
13 dated earlier, 1 the same month, 4 later
1807.06756 (2018-07)
SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilities
1906.02425 (2019-06)
Uncertainty-guided Continual Learning with Bayesian Neural Networks
2005.00558 (2020-05)
POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training
and 15 more not named here
last_boxed_only_string 17 other papers
6 dated earlier, 10 later, 1 same year, order not determinable
2309.06275 (2023-09)
Re-Reading Improves Reasoning in Large Language Models
2310.05914 (2023-10)
NEFTune: Noisy Embeddings Improve Instruction Finetuning
2024.findings-emnlp.407 (2024 (year only))
MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate
and 14 more not named here
last_boxed_only 6 other papers
3 dated earlier, 3 later
2404.02078 (2024-04)
Advancing LLM Reasoning Generalists with Preference Trees
2405.06680 (2024-05)
Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning Through Trap Problems
2406.14024 (2024-06)
LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
and 3 more not named here
only_until_first_boxed_from_tokens 6 other papers
4 dated earlier, 2 later
2404.02078 (2024-04)
Advancing LLM Reasoning Generalists with Preference Trees
2405.06680 (2024-05)
Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning Through Trap Problems
2405.15179 (2024-05)
VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
and 3 more not named here
is_digit 4 other papers
4 dated earlier
2309.17452 (2023-09)
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
2310.14747 (2023-10)
MCC-KD: Multi-CoT Consistent Knowledge Distillation
2403.00799 (2024-03)
An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning
and 1 more not named here
math_equal 3 other papers
3 dated earlier
2309.17452 (2023-09)
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
2403.00799 (2024-03)
An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning
2405.15179 (2024-05)
VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
math_equal_process 3 other papers
3 dated earlier
2309.17452 (2023-09)
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
2403.00799 (2024-03)
An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning
2405.15179 (2024-05)
VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
post_process 2 other papers
1 dated earlier, 1 later
2312.00700 (2023-12)
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
2602.01267 (2026-02)
Diving into Kronecker Adapters: Component Design Matters

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

Parameter-efficient fine-tuning (PEFT) has become a de facto standard for adapting large language models (LLMs). However, we identify a critical vulnerability within popular low-rank adaptation methods such as LoRA: they can exacerbate "Catastrophic Inheritance" - the unchecked propagation of biases, noise, and data imbalances from pre-training. This phenomenon can degrade model robustness and fairness, undermining the benefits of efficient adaptation. To address this, we introduce Bias-Alleviating Low-Rank Adaptation (BA-LoRA). Our approach is founded on a principled decomposition of Catastrophic Inheritance into three core challenges: Knowledge Drift, Representation Collapse, and Overfitting to Noise. BA-LoRA systematically mitigates these issues by incorporating a trio of targeted regularizers: consistency, diversity, and an SVD-based term, designed to preserve core knowledge, promote representational richness, and encourage robust, low-rank output representations, respectively. We conduct comprehensive evaluations on a suite of Natural Language Generation (NLG) and Natural Language Understanding (NLU) tasks using diverse, prominent open-source language models (e.g., LLaMA-2-7B and DeBERTa-v3-base). Our results show that BA-LoRA not only outperforms state-of-the-art LoRA variants in terms of performance and stability, but also demonstrates superior robustness and bias mitigation on targeted evaluations. These results provide evidence that BA-LoRA can counteract the adverse effects of Catastrophic Inheritance.

For agents

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

get_harvested_code_for_paper("2408.04556")
get_code_for_paper("2408.04556")
have("2408.04556")

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

curl https://syntology.ai/api/ran/2408.04556.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.04556.svg)](https://syntology.ai/paper/2408.04556)

Connect an agent — have() is free.