Questioning the survey responses of large language models
R Dominguez-Olmedo, M Hardt… - arXiv preprint arXiv …, 2023 - arxiv.org
As large language models increase in capability, researchers have started to conduct
surveys of all kinds on these models with varying scientific motivations. In this work, we …
surveys of all kinds on these models with varying scientific motivations. In this work, we …
Social bias evaluation for large language models requires prompt variations
Warning: This paper contains examples of stereotypes and biases. Large Language Models
(LLMs) exhibit considerable social biases, and various studies have tried to evaluate and …
(LLMs) exhibit considerable social biases, and various studies have tried to evaluate and …
[PDF][PDF] Metrics for what, metrics for whom: assessing actionability of bias evaluation metrics in NLP
This paper introduces the concept of actionability in the context of bias measures in natural
language processing (NLP). We define actionability as the degree to which a …
language processing (NLP). We define actionability as the degree to which a …
Rt-lm: Uncertainty-aware resource management for real-time inference of language models
Recent advancements in language models (LMs) have gained substantial attentions on their
capability to generate human-like responses. Though exhibiting a promising future for …
capability to generate human-like responses. Though exhibiting a promising future for …
Mitigating bias for question answering models by tracking bias influence
Models of various NLP tasks have been shown to exhibit stereotypes, and the bias in the
question answering (QA) models is especially harmful as the output answers might be …
question answering (QA) models is especially harmful as the output answers might be …
InnerThoughts: Disentangling Representations and Predictions in Large Language Models
D Chételat, J Cotnareanu, R Thompson… - arXiv preprint arXiv …, 2025 - arxiv.org
Large language models (LLMs) contain substantial factual knowledge which is commonly
elicited by multiple-choice question-answering prompts. Internally, such models process the …
elicited by multiple-choice question-answering prompts. Internally, such models process the …
[PDF][PDF] Think Twice Before You Answer: Mitigating Biases of Question Answering Models
BL Mikula - is.muni.cz
Abstract Large Language Models based on Transformer architecture hold state-of-the-art in
a majority of Natural Language Modeling tasks. Nevertheless, these models tend to learn …
a majority of Natural Language Modeling tasks. Nevertheless, these models tend to learn …