Language (technology) is power: A critical survey of" bias" in nlp
We survey 146 papers analyzing" bias" in NLP systems, finding that their motivations are
often vague, inconsistent, and lacking in normative reasoning, despite the fact that …
often vague, inconsistent, and lacking in normative reasoning, despite the fact that …
Large pre-trained language models contain human-like biases of what is right and wrong to do
Artificial writing is permeating our lives due to recent advances in large-scale, transformer-
based language models (LMs) such as BERT, GPT-2 and GPT-3. Using them as pre-trained …
based language models (LMs) such as BERT, GPT-2 and GPT-3. Using them as pre-trained …
Quark: Controllable text generation with reinforced unlearning
Large-scale language models often learn behaviors that are misaligned with user
expectations. Generated text may contain offensive or toxic language, contain significant …
expectations. Generated text may contain offensive or toxic language, contain significant …
A survey on bias in deep NLP
I Garrido-Muñoz, A Montejo-Ráez… - Applied Sciences, 2021 - mdpi.com
Deep neural networks are hegemonic approaches to many machine learning areas,
including natural language processing (NLP). Thanks to the availability of large corpora …
including natural language processing (NLP). Thanks to the availability of large corpora …
The moral integrity corpus: A benchmark for ethical dialogue systems
Conversational agents have come increasingly closer to human competence in open-
domain dialogue settings; however, such models can reflect insensitive, hurtful, or entirely …
domain dialogue settings; however, such models can reflect insensitive, hurtful, or entirely …
Risk taxonomy, mitigation, and assessment benchmarks of large language model systems
Large language models (LLMs) have strong capabilities in solving diverse natural language
processing tasks. However, the safety and security issues of LLM systems have become the …
processing tasks. However, the safety and security issues of LLM systems have become the …
Debiasing pre-trained language models via efficient fine-tuning
An explosion in the popularity of transformer-based language models (such as GPT-3,
BERT, RoBERTa, and ALBERT) has opened the doors to new machine learning …
BERT, RoBERTa, and ALBERT) has opened the doors to new machine learning …
Bias and fairness in large language models: A survey
Rapid advancements of large language models (LLMs) have enabled the processing,
understanding, and generation of human-like text, with increasing integration into systems …
understanding, and generation of human-like text, with increasing integration into systems …
Are personalized stochastic parrots more dangerous? evaluating persona biases in dialogue systems
Recent advancements in Large Language Models empower them to follow freeform
instructions, including imitating generic or specific demographic personas in conversations …
instructions, including imitating generic or specific demographic personas in conversations …
Language models for German text simplification: Overcoming parallel data scarcity through style-specific pre-training
M Anschütz, J Oehms, T Wimmer, B Jezierski… - arXiv preprint arXiv …, 2023 - arxiv.org
Automatic text simplification systems help to reduce textual information barriers on the
internet. However, for languages other than English, only few parallel data to train these …
internet. However, for languages other than English, only few parallel data to train these …