Pythia releases 16 identically trained LLMs with full checkpoints and data tools to study training dynamics, scaling, memorization, and bias in language models.
F rench C row S -Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than E nglish
5 Pith papers cite this work, alongside 34 external citations. Polarity classification is still indexing.
5
Pith papers citing it
34
external citations · OpenAlex
fields
cs.CL 5representative citing papers
A human-LLM collaborative pipeline yields EspanStereo, a multi-country Spanish stereotype dataset that exposes region-specific biases in Spanish LLMs and diverges sharply from English-centric resources.
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.
H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.
BLOOM is a 176B-parameter open-access multilingual language model trained on the ROOTS corpus that achieves competitive performance on benchmarks, with improved results after multitask prompted finetuning.
citing papers explorer
-
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
Pythia releases 16 identically trained LLMs with full checkpoints and data tools to study training dynamics, scaling, memorization, and bias in language models.
-
Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration
A human-LLM collaborative pipeline yields EspanStereo, a multi-country Spanish stereotype dataset that exposes region-specific biases in Spanish LLMs and diverges sharply from English-centric resources.
-
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.
-
Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles
H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.
-
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BLOOM is a 176B-parameter open-access multilingual language model trained on the ROOTS corpus that achieves competitive performance on benchmarks, with improved results after multitask prompted finetuning.