English
Related papers

Related papers: Token-Level Entropy Reveals Demographic Disparitie…

200 papers

Autoregressive neural language models (LMs) generate a probability distribution over tokens at each time step given a prompt. In this work, we attempt to systematically understand the probability distributions that LMs can produce, showing…

Computation and Language · Computer Science 2025-09-23 Haojin Wang , Zining Zhu , Freda Shi

The ubiquity of offensive and hateful content on online fora necessitates the need for automatic solutions that detect such content competently across target groups. In this paper we show that text classification models trained on large…

Computation and Language · Computer Science 2021-12-08 Darsh J Shah , Sinong Wang , Han Fang , Hao Ma , Luke Zettlemoyer

Vision-language models such as OpenAI GPT-4o can transcribe mathematical documents directly from images, yet their token-level confidence signals are seldom used to pinpoint local recognition mistakes. We present an entropy-heat-mapping…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Alexei Kaltchenko

This work describes a large-scale analysis of sentiment associations in popular word embedding models along the lines of gender and ethnicity but also along the less frequently studied dimensions of socioeconomic status, age, sexual…

Computers and Society · Computer Science 2020-07-01 David Rozado

Tokenization is a necessary component within the current architecture of many language mod-els, including the transformer-based large language models (LLMs) of Generative AI, yet its impact on the model's cognition is often overlooked. We…

Deploying LLMs raises two coupled challenges: (1) monitoring--estimating where a model underperforms as traffic and domains drift--and (2) improvement--prioritizing data acquisition to close the largest performance gaps. We test whether an…

Computation and Language · Computer Science 2026-05-27 Pedro Memoli Buffa , Luciano Del Corro

Large Language Models (LLMs) offer a lucrative promise for scalable content moderation, including hate speech detection. However, they are also known to be brittle and biased against marginalised communities and dialects. This requires…

Computation and Language · Computer Science 2025-10-14 Ananya Malik , Kartik Sharma , Shaily Bhatt , Lynnette Hui Xian Ng

Authorship attribution techniques are increasingly being used in online contexts such as sock puppet detection, malicious account linking, and cross-platform account linking. Yet, it is unknown whether these models perform equitably across…

Social and Information Networks · Computer Science 2025-10-23 Jasmin Wyss , Rebekah Overdorf

Across cultures, names tell a lot about their bearers as they carry deep personal and cultural significance. Names also serve as powerful signals of gender, race, and status in the social hierarchy - a pecking order in which individual…

Computation and Language · Computer Science 2025-04-16 Annabella Sakunkoo , Jonathan Sakunkoo

Authorship attribution models fine-tuned with the same pretrained encoder, data, and loss can differ four-fold in performance depending only on their scoring mechanism. We use mechanistic interpretability tools to explain this gap.…

Computation and Language · Computer Science 2026-05-27 Francis Kulumba , Guillaume Vimont , Laurent Romary , Florian Cafiero

Contextual entropy is a psycholinguistic measure capturing the anticipated difficulty of processing a word just before it is encountered. Recent studies have tested for entropy-related effects as a potential complement to well-known effects…

Computation and Language · Computer Science 2025-07-31 Christian Clark , Byung-Doh Oh , William Schuler

Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as 'ing' or whole words. Recent literature has repeatedly shown the…

Computation and Language · Computer Science 2023-10-19 Avijit Thawani , Saurabh Ghanekar , Xiaoyuan Zhu , Jay Pujara

Many sequence-to-sequence generation tasks, including machine translation and text-to-speech, can be posed as estimating the density of the output y given the input x: p(y|x). Given this interpretation, it is natural to evaluate…

Machine Learning · Computer Science 2020-02-19 Jason Lee , Dustin Tran , Orhan Firat , Kyunghyun Cho

In this paper, we apply a method to quantify biases associated with named entities from various countries. We create counterfactual examples with small perturbations on target-domain data instead of relying on templates or specific datasets…

Computation and Language · Computer Science 2024-11-26 Valentin Barriere , Sebastian Cifuentes

Semantic leakage is a phenomenon recently introduced by Gonen et al. (2024). It refers to a situation in which associations learnt from the training data emerge in language model generations in an unexpected and sometimes undesired way.…

Computation and Language · Computer Science 2025-01-14 Veronika Smilga

Large Language Models (LLMs) are finding applications in all aspects of life, but their susceptibility to biases, particularly gender stereotyping, raises ethical concerns. This study introduces a novel methodology, a persona-based…

Computers and Society · Computer Science 2025-02-18 Rajesh Ranjan , Shailja Gupta , Surya Naranyan Singh

In recent years, the fine-tuned generative models have been proven more powerful than the previous tagging-based or span-based models on named entity recognition (NER) task. It has also been found that the information related to entities,…

Computation and Language · Computer Science 2024-06-12 Guochao Jiang , Ziqin Luo , Yuchen Shi , Dixuan Wang , Jiaqing Liang , Deqing Yang

Large language models (LLMs) acquire beliefs about gender from training data and can therefore generate text with stereotypical gender attitudes. Prior studies have demonstrated model generations favor one gender or exhibit stereotypes…

Computation and Language · Computer Science 2024-10-16 Sharon Levy , William D. Adler , Tahilin Sanchez Karver , Mark Dredze , Michelle R. Kaufman

Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude larger than what biological learners require. An alternative paradigm has emerged in which…

Machine Learning · Computer Science 2026-05-28 Daniel J. Korchinski , Alessandro Favero , Matthieu Wyart

We investigate in this paper how distributions of occupations with respect to gender is reflected in pre-trained language models. Such distributions are not always aligned to normative ideals, nor do they necessarily reflect a descriptive…

Computation and Language · Computer Science 2023-04-13 Samia Touileb , Lilja Øvrelid , Erik Velldal