Browse State-of-the-Art › Bias Detection
Bias Detection
80 papers with code · 5 benchmarks · 11 datasets archive 2025-07-28
Bias detection is the task of detecting and measuring racism, sexism and otherwise discriminatory behavior in a model (Source: https://stereoset.mit.edu/)
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 2 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): StereoSet (2 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| StereoSet (11 rows) | GPT-2 (small) | StereoSet: Measuring stereotypical bias in pretrained language models | code | — | Compare |
| rt-inod-bias (5 rows) | GPT-4 | Benchmarking Llama2, Mistral, Gemma and GPT for Factuality,... | code | Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified | Compare |
| ICAT LLM bias (1 row) | BAD | BAD: BiAs Detection for Large Language Models in the context of... | code | — | Compare |
| PlantVillage_8px (1 row) | RandomForest_default_hyperparameters | Uncovering bias in the PlantVillage dataset | code | — | Compare |
| Wiki Neutrality Corpus (1 row) | RoBERTa+ALBERT | Towards Detection of Subjective Bias using Contextualized Word Embeddings | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
11 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 199 · with a code link: 80 · where Syntology ran a sample: 11 (9 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (11 of 199 tagged: 9 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 199, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
20 Apr 2020 3 repositories listedSince pretrained language models are trained on large real world data, they are known to capture stereotypical biases.
-
16 Sep 2023 2 repositories listedLLMs are increasingly powerful and widely used to assist users in a variety of tasks.
-
28 Jan 2023 2 repositories listedHence, we also contribute a new, large Swedish bias-labelled dataset (of 2 million samples), translated from the English version and train the SotA mT5 model on it.
-
6 Jun 2020 2 repositories listed Syntology official (archive's flag): 6 ran · 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 5 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples) · 6 pointer-only (licence)Furthermore, we develop two methods, Intersectional Bias Detection (IBD) and Emergent Intersectional Bias Detection (EIBD), to automatically identify the intersectional biases and emergent intersectional biases from…
-
2 Dec 2019 2 repositories listedTo address these drawbacks, we formalize a method for automating the selection of interesting PDPs and extend PDPs beyond showing single features to show the model response along arbitrary directions, for example in raw…
-
1 Jun 2025 1 repository listedWe present Concept Trajectory Analysis (CTA), an interpretability method that tracks how neural networks organize concepts by following their paths through clustered activation spaces across layers.
-
19 May 2025 1 repository listedMedia bias detection is a critical task in ensuring fair and balanced information dissemination, yet it remains challenging due to the subjectivity of bias and the scarcity of high-quality annotated data.
-
16 May 2025 1 repository listedGenerative AI systems can help spread information but also misinformation and biases, potentially undermining the UN Sustainable Development Goals (SDGs).
-
1 May 2025 1 repository listedA key objective in spatial analysis is to model spatial relationships and infer spatial processes to generate knowledge from spatial data, which has been largely based on spatial statistical methods.
-
21 Feb 2025 1 repository listedThere is general agreement for the remaining 3 personality dimensions: both sides observe at most small differences across gender.
-
22 Dec 2024 1 repository listedThe integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) opens new avenues for addressing complex challenges in multimodal content analysis, particularly in biased news detection.
-
16 Dec 2024 1 repository listedWe introduce MT-LENS, a framework designed to evaluate Machine Translation (MT) systems across a variety of tasks, including translation quality, gender bias detection, added toxicity, and robustness to misspellings.
-
17 Nov 2024 1 repository listedOur classifier, fine-tuned on this dataset, surpasses all of the annotator LLMs by 5-9 percent in Matthews Correlation Coefficient (MCC) and performs close to or outperforms the model trained on human-labeled data when…
-
Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach12 Nov 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)Large Language Models (LLMs) often perpetuate biases in pronoun usage, leading to misrepresentation or exclusion of queer individuals.
-
17 Oct 2024 1 repository listedThis study displays the problems with the current benchmarks for measuring demographic bias in Vision Language Models and introduces both a more effective dataset for measuring bias and a novel and interpretable…
-
10 Oct 2024 1 repository listedThe detection of bias in natural language processing (NLP) is a critical challenge, particularly with the increasing use of large language models (LLMs) in various domains.
-
9 Oct 2024 1 repository listedOur approach features: (1) a synthetic emotional instruct dataset for both pre-training and fine-tuning stages, (2) a Metric Projector that delegates classification from the language model allowing for more efficient…
-
3 Oct 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)To that end, our study investigates the presence of implicit gender biases in multi-agent LLM interactions and proposes two strategies to mitigate these biases.
-
25 Sep 2024 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples) · 10 pointer-only (licence)Our model allows any large language model to perform counterfactual token generation at almost no cost in comparison with vanilla token generation, it is embarrassingly simple to implement, and it does not require any…
-
4 Sep 2024 1 repository listedIn IDH mutation classification, HIPPO more robustly identified the pathology regions responsible for false negatives compared to attention, suggesting its potential to outperform attention in explaining model decisions.
-
29 Aug 2024 1 repository listedOpenBias detects and quantifies biases, while GradBias determines the contribution of individual prompt words on biases.
-
26 Jul 2024 1 repository listedThe project BIAS: Mitigating Diversity Biases of AI in the Labor Market is a four-year project funded by the European commission and supported by the Swiss State Secretariat for Education, Research and Innovation (SERI).
-
3 Jul 2024 1 repository listedThe rapid growth of Large Language Models (LLMs) has put forward the study of biases as a crucial field.
-
1 Jul 2024 1 repository listedIn this paper, we apply a method to quantify biases associated with named entities from various countries.
-
1 Jun 2024 1 repository listedData derived from the realm of the social sciences is often produced in digital text form, which motivates its use as a source for natural language processing methods.
-
20 May 2024 1 repository listedMachine Learning algorithms (ML) impact virtually every aspect of human lives and have found use across diverse sectors including healthcare, finance, and education.
-
16 May 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)It is often desirable to distill the capabilities of large language models (LLMs) into smaller student models due to compute and memory constraints.
-
15 Apr 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples)In this research, we used OpenAI GPT as point of comparison since it excels at all levels of safety.
-
11 Apr 2024 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples) · 10 pointer-only (licence)In this paper, we tackle the challenge of open-set bias detection in text-to-image generative models presenting OpenBias, a new pipeline that identifies and quantifies the severity of biases agnostically, without access…
-
28 Mar 2024 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 1 pointer-only (licence)Neural networks trained on biased datasets tend to inadvertently learn spurious correlations, hindering generalization.
-
26 Mar 2024 1 repository listed
-
27 Feb 2024 1 repository listed
-
1 Feb 2024 1 repository listed
-
1 Jan 2024 1 repository listed
-
26 Dec 2023 1 repository listed
-
28 Jul 2023 1 repository listed
-
1 Jun 2023 1 repository listed
-
29 May 2023 1 repository listed
-
24 May 2023 1 repository listed Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
22 May 2023 1 repository listed
-
21 May 2023 1 repository listed
-
17 May 2023 1 repository listed
-
25 Apr 2023 1 repository listed
-
8 Apr 2023 1 repository listed
-
16 Nov 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
15 Nov 2022 1 repository listed
-
29 Sep 2022 1 repository listed
-
9 Aug 2022 1 repository listed
-
14 Jul 2022 1 repository listed
-
1 Jul 2022 1 repository listed
-
9 Jun 2022 1 repository listed
-
22 May 2022 1 repository listed
-
22 May 2022 1 repository listed
-
28 Apr 2022 1 repository listed
-
17 Mar 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
23 Dec 2021 1 repository listed
-
22 Dec 2021 1 repository listed
-
1 Dec 2021 1 repository listed
-
1 Nov 2021 1 repository listed
-
1 Nov 2021 1 repository listed
-
1 Nov 2021 1 repository listed
-
19 Sep 2021 1 repository listed
-
9 Sep 2021 1 repository listed
-
7 Sep 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
1 Sep 2021 1 repository listed
-
1 Aug 2021 1 repository listed
-
8 Jun 2021 1 repository listed
-
15 Apr 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
1 Apr 2021 1 repository listed
-
3 Dec 2020 1 repository listed
-
20 Oct 2020 1 repository listed
-
6 Oct 2020 1 repository listed
-
5 Oct 2020 1 repository listed
-
5 May 2020 1 repository listed
-
16 Feb 2020 1 repository listed
-
25 Nov 2019 1 repository listed
-
20 Oct 2019 1 repository listed
-
1 Sep 2019 1 repository listed
-
1 Aug 2019 1 repository listed
-
23 May 2019 1 repository listed
-
Cascading Adversarial Bias from Injection to Distillation in Language Models30 May 2025 0 repositories listed
-
Can we Debias Social Stereotypes in AI-Generated Images? Examining Text-to-Image Outputs and User Perceptions27 May 2025 0 repositories listed
-
Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector21 May 2025 0 repositories listed
-
21 May 2025 0 repositories listed
-
Efficient Fairness Testing in Large Language Models: Prioritizing Metamorphic Relations for Bias Detection9 May 2025 0 repositories listed
-
BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models30 Apr 2025 0 repositories listed
-
Toward Holistic Evaluation of Recommender Systems Powered by Generative Models9 Apr 2025 0 repositories listed
-
Neutralizing the Narrative: AI-Powered Debiasing of Online News Articles4 Apr 2025 0 repositories listed
-
STOOD-X methodology: using statistical nonparametric test for OOD Detection Large-Scale datasets enhanced with explainability3 Apr 2025 0 repositories listed
-
On the Mutual Influence of Gender and Occupation in LLM Representations9 Mar 2025 0 repositories listed
-
Fine-Grained Bias Detection in LLM: Enhancing detection mechanisms for nuanced biases8 Mar 2025 0 repositories listed
-
Cognitive Bias Detection Using Advanced Prompt Engineering7 Mar 2025 0 repositories listed
-
Visual Reasoning Evaluation of Grok, Deepseek Janus, Gemini, Qwen, Mistral, and ChatGPT23 Feb 2025 0 repositories listed
-
Detecting Linguistic Bias in Government Documents Using Large language Models19 Feb 2025 0 repositories listed
-
Towards Equitable AI: Detecting Bias in Using Large Language Models for Marketing18 Feb 2025 0 repositories listed
-
BiaSWE: An Expert Annotated Dataset for Misogyny Detection in Swedish11 Feb 2025 0 repositories listed
-
FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing6 Feb 2025 0 repositories listed
-
LLMs can be easily Confused by Instructional Distractions5 Feb 2025 0 repositories listed
-
Bias Detection via Maximum Subgroup Discrepancy4 Feb 2025 0 repositories listed
-
Sample Complexity of Bias Detection with Subsampled Point-to-Subspace Distances4 Feb 2025 0 repositories listed
Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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