mlsanityData to 14 Oct 2026

Uncovering Implicit Bias in Large Language Models with Concept Learning Dataset

arXiv 2510.01219 ↗First posted 21 Sep 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce a dataset of concept learning tasks that helps uncover implicit biases in large language models. Using in-context concept learning experiments, we found that language models may have a bias toward upward monotonicity in quantifiers; such bias is less apparent when the model is tested by direct prompting without concept learning components. This demonstrates that in-context concept learning can be an effective way to discover hidden biases in language models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 22 references that are in the map. First posted on arXiv 21 Sep 2025.

Builds on

11 of 22 references.

References · 11

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  3. 2022Emergent Abilities of Large Language Modelscited by 2,512
  4. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  5. 20242 OLMo 2 Furiouscited by 340
  6. 2023"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letterscited by 199
  7. 2021Language Models Use Monotonicity to Assess NPI Licensingcited by 31
  8. 2025Unmasking Implicit Bias: Evaluating Persona-Prompted LLM Responses in Power-Disparate Social Scenarioscited by 26
  9. 2025LLM360 K2: Building a 65B 360-Open-Source Large Language Model from Scratchcited by 15
  10. 2024Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approachcited by 12
  11. 2024Minimization of Boolean Complexity in In-Context Concept Learningcited by 2

Built on by

Not cited yet.