SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.09141 · 2026

Identity-Robust Language Model Generation via Content Integrity Preservation

Miao Zhang, Rumi Chunara, Kelly Chen, Md Tanjim

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 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 2 have no contract verdict; 5 failures of our instrument; 4 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; 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/2601.09141.json · badge: /api/ran/2601.09141.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
XMUDM/Guide-Align canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
shmsw25/AmbigQA community
Papers with Code archive
3 ran · 2 no recorded run
FunctionStatusWhere it lives
dot_product_scores Ran
ran; our contract draft was wrong, not the code
XMUDM/Guide-Align/code/DPR/dpr/models/biencoder.py
pointer only (licence: NONE); the stored copy get_code serves, from facebookresearch/dpr, is pointer only (licence: NOASSERTION) · get_code("928414780ee23e45")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XMUDM/Guide-Align 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.

BeamHypotheses Ran
ran on a synthesized input
shmsw25/AmbigQA/codes/models/seq2seq_with_prefix.py
pointer only (licence: NONE) · get_code("019eaaabbb611d25")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shmsw25/AmbigQA 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.

calc_banned_bad_words_ids Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shmsw25/AmbigQA/codes/models/seq2seq_with_prefix.py
pointer only (licence: NONE) · get_code("dfa20adee3bba826")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shmsw25/AmbigQA 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.

calc_banned_ngram_tokens Ran
ran on a synthesized input
shmsw25/AmbigQA/codes/models/seq2seq_with_prefix.py
pointer only (licence: NONE) · get_code("8d77347cfa15b834")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shmsw25/AmbigQA 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.

chunk_list Ran
ran; our contract draft was wrong, not the code
XMUDM/Guide-Align/code/evaluate_do_not_answer.py
pointer only (licence: NONE) · get_code("7d35b0e8d04e1cc4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XMUDM/Guide-Align 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.

cosine_scores Ran
ran; our contract draft was wrong, not the code
XMUDM/Guide-Align/code/DPR/dpr/models/biencoder.py
pointer only (licence: NONE); the stored copy get_code serves, from facebookresearch/dpr, is pointer only (licence: NOASSERTION) · get_code("4c7d079ed8d8dd58")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XMUDM/Guide-Align 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
XMUDM/Guide-Align/code/augmentation_prompt.py
pointer only (licence: NONE) · get_code("54b95bf60dbf6155")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XMUDM/Guide-Align 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.

MyBart Not yet run
unverified (harvested, no recorded run)
shmsw25/AmbigQA/codes/models/seq2seq_with_prefix.py
pointer only (licence: NONE) · get_code("d566bf37a637c742")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shmsw25/AmbigQA 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.

MyBartWithPrefix Not yet run
unverified (harvested, no recorded run)
shmsw25/AmbigQA/codes/models/seq2seq_with_prefix.py
pointer only (licence: NONE) · get_code("9dab0b10ec6f200c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shmsw25/AmbigQA 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.

create_input Not yet run
unverified (harvested, no recorded run)
XMUDM/Guide-Align/code/generate_response.py
pointer only (licence: NONE) · get_code("7878cd9260ffece4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XMUDM/Guide-Align 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.

generate_prompt Not yet run
unverified (harvested, no recorded run)
XMUDM/Guide-Align/code/generate_response.py
pointer only (licence: NONE) · get_code("9fdbd9ee47ef2f75")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XMUDM/Guide-Align 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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
calc_banned_ngram_tokens
brick of this paper's assembly: helper
8 other papers
8 dated earlier
1910.13461 (2019-10)
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
2106.01317 (2021-06)
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
2109.04096 (2021-09)
A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
and 5 more not named here
cosine_scores 7 other papers
7 dated earlier
1911.03868 (2019-11)
Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering
2106.05346 (2021-06)
End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering
2205.09843 (2022-05)
Table Retrieval May Not Necessitate Table-specific Model Design
and 4 more not named here
dot_product_scores 7 other papers
7 dated earlier
1911.03868 (2019-11)
Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering
2106.05346 (2021-06)
End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering
2205.09843 (2022-05)
Table Retrieval May Not Necessitate Table-specific Model Design
and 4 more not named here
calc_banned_bad_words_ids
brick of this paper's assembly: helper
3 other papers
3 dated earlier
2309.01017 (2023-09)
Contrastive Grouping with Transformer for Referring Image Segmentation
2312.06149 (2023-12)
Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding
2402.02503 (2024-02)
GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering
chunk_list 2 other papers
2 dated earlier
2025.naacl-long.579 (2025 (year only))
ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding
2501.13106 (2025-01)
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding

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

Large Language Model (LLM) outputs often vary across user sociodemographic attributes, leading to disparities in factual accuracy, utility, and safety, even for objective questions where demographic information is irrelevant. Unlike prior work on stereotypical or representational bias, this paper studies identitydependent degradation of core response quality. We show empirically that such degradation arises from biased generation behavior, despite factual knowledge being robustly encoded across identities. Motivated by this mismatch, we propose a lightweight, training-free framework for identity-robust generation that selectively neutralizes non-critical identity information while preserving semantically essential attributes, thus maintaining output content integrity. Experiments across four benchmarks and 18 sociodemographic identities demonstrate an average 77% reduction in identitydependent bias compared to vanilla prompting and a 45% reduction relative to prompt-based defenses. Our work addresses a critical gap in mitigating the impact of user identity cues in prompts on core generation quality. Yes. Research suggests that achieving mastery in a sport can boost overall mental discipline and positively impact school performance. User identity: full-time worker User identity: unemployed We find: Internal knowledge is stable. User identity skews answers. Question: Does achieving mastery in a sport help make you smarter in school? Identity-neutral prompt rewriting and content generation STAGE 3 While there may be correlations, such as improved discipline or time management, there is no strong scientific evidence to prove a causal relationship.

For agents

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

get_harvested_code_for_paper("2601.09141")
get_code_for_paper("2601.09141")
have("2601.09141")

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

curl https://syntology.ai/api/ran/2601.09141.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.09141.svg)](https://syntology.ai/paper/2601.09141)

Connect an agent — have() is free.