No article text was recorded for this version.
perplexity-based bias quantification
Version 1 of 1113 papers122 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation
- Blog: InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct
- Blog: On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations
- Blog: Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)
- Blog: On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations
- Blog: LIBRA: Measuring Bias of Large Language Model from a Local Context
- Blog: BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation
- Blog: Can a Prediction's Rank Offer a More Accurate Quantification of Bias? A Case Study Measuring Sexism in Debiased Language Models
- Blog: AutoBiasTest: Controllable Sentence Generation for Automated and Open-Ended Social Bias Testing in Language Models
- Blog: A Transparent Framework for Evaluating Unintended Demographic Bias in Word Embeddings
- Blog: Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers
- Blog: Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning
- Blog: A Multilingual Perspective on Probing Gender Bias
- Blog: More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation
- Blog: Towards WinoQueer: Developing a Benchmark for Anti-Queer Bias in Large Language Models
- Blog: McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models
- Blog: Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
- Blog: An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models
- Blog: Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases
- Blog: Empowering Domain Experts to Detect Social Bias in Generative AI with User-Friendly Interfaces
- Blog: Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation
- Blog: Finspector: A Human-Centered Visual Inspection Tool for Exploring and Comparing Biases among Foundation Models
- Blog: Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models
- Blog: Filipino Benchmarks for Measuring Sexist and Homophobic Bias in Multilingual Language Models from Southeast Asia
- Blog: Assumed Identities: Quantifying Gender Bias in Machine Translation of Gender-Ambiguous Occupational Terms
- Blog: EuroGEST: Investigating gender stereotypes in multilingual language models
- Blog: Justice in Judgment: Unveiling (Hidden) Bias in LLM-Assisted Peer Reviews
- Blog: Examining Alignment of Large Language Models through Representative Heuristics: the case of political stereotypes
- Blog: Context Matters: A Pragmatic Study of PLMs' Negation Understanding
- Blog: ImageCaptioner2: Image Captioner for Image Captioning Bias Amplification Assessment
- Blog: WinoQueer: A Community-in-the-Loop Benchmark for Anti-LGBTQ+ Bias in Large Language Models
- Blog: Mitigating Bias for Question Answering Models by Tracking Bias Influence
- Blog: Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can Balance
- Blog: GBEM-UA: Gender Bias Evaluation and Mitigation for Ukrainian Large Language Models
- Blog: Beyond Performance: Quantifying and Mitigating Label Bias in LLMs
- Blog: Global Gallery: The Fine Art of Painting Culture Portraits through Multilingual Instruction Tuning
- Blog: Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG
- Blog: WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorization
- Blog: In-Contextual Gender Bias Suppression for Large Language Models
- Blog: Having Beer after Prayer? Measuring Cultural Bias in Large Language Models
- Blog: Unmasking Style Sensitivity: A Causal Analysis of Bias Evaluation Instability in Large Language Models
- Blog: Distributional Readout: A Memorization Regime in Autoregressive Generative Models
- Blog: Questioning the Survey Responses of Large Language Models
- Blog: B-score: Detecting biases in large language models using response history
- Blog: Choices Speak Louder than Questions
- Blog: Lost in Inference: Rediscovering the Role of Natural Language Inference for Large Language Models
- Blog: Can Large Langauge Model Comprehend Ancient Chinese? A Preliminary Test on ACLUE
- Blog: Perplexity-aware Correction for Robust Alignment with Noisy Preferences
- Blog: UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
- Blog: Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview
- Blog: Introducing MARB — A Dataset for Studying the Social Dimensions of Reporting Bias in Language Models
- Blog: Prompting is not a substitute for probability measurements in large language models
- Blog: Sense Embeddings are also Biased - Evaluating Social Biases in Static and Contextualised Sense Embeddings
- Blog: BehaviorBox: Automated Discovery of Fine-Grained Performance Differences Between Language Models
- Blog: Reward Models Inherit Value Biases from Pretraining
- Blog: Constructing Holistic Measures for Social Biases in Masked Language Models
- Blog: From Words to Worlds: Compositionality for Cognitive Architectures
- Blog: Unmasking Contextual Stereotypes: Measuring and Mitigating BERT’s Gender Bias
- Blog: All Should Be Equal in the Eyes of LMs: Counterfactually Aware Fair Text Generation
- Blog: CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models
Showing 60 of 113 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_perplexity_based_bias_quantification_4f46ddd0,
title = {perplexity-based bias quantification},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/perplexity-based-bias-quantification/rdr_4f46ddd009924f1fb86d1b7c27b2f91b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_perplexity_based_bias_quantification_4f46ddd0_v1,
title = {perplexity-based bias quantification},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/perplexity-based-bias-quantification/rdr_4f46ddd009924f1fb86d1b7c27b2f91b/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}