A Dutch BERT model encodes gender linearly by epoch 20 but does not dynamically update its representations when explicit female cues contradict learned stereotypical associations in short sentence templates.
and Rudinger, Rachel
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
SPAGBias reveals that LLMs form nuanced gender associations with specific urban micro-spaces that exceed real-world distributions and produce failures in planning and descriptive tasks.
BIG-bench is a 204-task benchmark that measures scaling trends, calibration, and absolute limitations of language models across knowledge, reasoning, and social domains.
BBQ is a new benchmark dataset showing that QA models often default to social stereotypes, achieving up to 3.4 points higher accuracy when the correct answer aligns with bias.
LLMs contain identifiable COCO neurons that enable implicit self-correction against stereotypes; targeted editing of these neurons improves fairness and robustness to jailbreaks while preserving generation quality.
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.
citing papers explorer
-
Is She Even Relevant? When BERT Ignores Explicit Gender Cues
A Dutch BERT model encodes gender linearly by epoch 20 but does not dynamically update its representations when explicit female cues contradict learned stereotypical associations in short sentence templates.
-
SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models
SPAGBias reveals that LLMs form nuanced gender associations with specific urban micro-spaces that exceed real-world distributions and produce failures in planning and descriptive tasks.
-
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench is a 204-task benchmark that measures scaling trends, calibration, and absolute limitations of language models across knowledge, reasoning, and social domains.
-
BBQ: A Hand-Built Bias Benchmark for Question Answering
BBQ is a new benchmark dataset showing that QA models often default to social stereotypes, achieving up to 3.4 points higher accuracy when the correct answer aligns with bias.
-
Modeling Implicit Conflict Monitoring Mechanisms against Stereotypes in LLMs
LLMs contain identifiable COCO neurons that enable implicit self-correction against stereotypes; targeted editing of these neurons improves fairness and robustness to jailbreaks while preserving generation quality.
-
StarCoder: may the source be with you!
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.