pith. machine review for the scientific record. sign in

The woman worked as a babysitter: On biases in language generation

4 Pith papers cite this work. Polarity classification is still indexing.

4 Pith papers citing it

representative citing papers

Is She Even Relevant? When BERT Ignores Explicit Gender Cues

cs.CL · 2026-05-08 · conditional · novelty 7.0

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.

StarCoder 2 and The Stack v2: The Next Generation

cs.SE · 2024-02-29 · accept · novelty 6.0

StarCoder2-15B matches or beats CodeLlama-34B on code tasks despite being smaller, and StarCoder2-3B outperforms prior 15B models, with open weights and exact training data identifiers released.

On the Opportunities and Risks of Foundation Models

cs.LG · 2021-08-16 · accept · novelty 6.0

Foundation models are large adaptable AI systems with emergent capabilities that offer broad opportunities but carry risks from homogenization, opacity, and inherited defects across downstream applications.

citing papers explorer

Showing 4 of 4 citing papers.

  • Is She Even Relevant? When BERT Ignores Explicit Gender Cues cs.CL · 2026-05-08 · conditional · none · ref 12

    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 cs.CL · 2026-04-16 · unverdicted · none · ref 55

    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.

  • StarCoder 2 and The Stack v2: The Next Generation cs.SE · 2024-02-29 · accept · none · ref 274

    StarCoder2-15B matches or beats CodeLlama-34B on code tasks despite being smaller, and StarCoder2-3B outperforms prior 15B models, with open weights and exact training data identifiers released.

  • On the Opportunities and Risks of Foundation Models cs.LG · 2021-08-16 · accept · none · ref 14

    Foundation models are large adaptable AI systems with emergent capabilities that offer broad opportunities but carry risks from homogenization, opacity, and inherited defects across downstream applications.