English
Related papers

Related papers: Challenges in Detoxifying Language Models

200 papers

This paper addresses the conceptual, methodological and technical challenges in studying large language models (LLMs) and the texts they produce from a quantitative linguistics perspective. It builds on a theoretical framework that…

Computation and Language · Computer Science 2024-08-30 Jiří Milička

Pretrained large language models have become indispensable for solving various natural language processing (NLP) tasks. However, safely deploying them in real world applications is challenging because they generate toxic content. To address…

Computation and Language · Computer Science 2023-02-16 Shrimai Prabhumoye , Mostofa Patwary , Mohammad Shoeybi , Bryan Catanzaro

The widespread of generative artificial intelligence has heightened concerns about the potential harms posed by AI-generated texts, primarily stemming from factoid, unfair, and toxic content. Previous researchers have invested much effort…

Computation and Language · Computer Science 2024-12-24 Shiyao Cui , Zhenyu Zhang , Yilong Chen , Wenyuan Zhang , Tianyun Liu , Siqi Wang , Tingwen Liu

Large language models can produce toxic or inappropriate text even for benign inputs, creating risks when deployed at scale. Detoxification is therefore important for safety and user trust, particularly when we want to reduce harmful…

Computation and Language · Computer Science 2026-02-04 Baturay Saglam , Dionysis Kalogerias

With the different roles that AI is expected to play in human life, imbuing large language models (LLMs) with different personalities has attracted increasing research interests. While the "personification" enhances human experiences of…

Artificial Intelligence · Computer Science 2025-09-22 Shuo Wang , Renhao Li , Xi Chen , Yulin Yuan , Derek F. Wong , Min Yang

Large language models (LLMs) are increasingly used to support the analysis of complex financial disclosures, yet their reliability, behavioral consistency, and transparency remain insufficiently understood in high-stakes settings. This…

Computation and Language · Computer Science 2026-01-21 Md Talha Mohsin

Having a clean dataset has been the foundational assumption of most natural language processing (NLP) systems. However, properly written text is rarely found in real-world scenarios and hence, oftentimes invalidates the aforementioned…

Computation and Language · Computer Science 2025-10-08 Ayush Singh , Navpreet Singh , Shubham Vatsal

The deployment of Large Language Models (LLMs) in diverse applications necessitates an assurance of safety without compromising the contextual integrity of the generated content. Traditional approaches, including safety-specific fine-tuning…

Computation and Language · Computer Science 2024-07-01 Shaina Raza , Ananya Raval , Veronica Chatrath

The rapid rise of Large Language Models (LLMs) has created new disruptive possibilities for persuasive communication, enabling fully-automated, personalized, and interactive content generation at an unprecedented scale. In this paper, we…

Computation and Language · Computer Science 2026-04-22 Sander Noels , Alexander Rogiers , Maarten Buyl , Tijl De Bie

Despite notable advances in large language models (LLMs), reliable evaluation of text generation tasks such as text style transfer (TST) remains an open challenge. Existing research has shown that automatic metrics often correlate poorly…

Computation and Language · Computer Science 2026-03-05 Vitaly Protasov , Nikolay Babakov , Daryna Dementieva , Alexander Panchenko

Public leaderboards increasingly suggest that large language models (LLMs) surpass human experts on benchmarks spanning academic knowledge, law, and programming. Yet most benchmarks are fully public, their questions widely mirrored across…

Artificial Intelligence · Computer Science 2026-03-18 Eshwar Reddy M , Sourav Karmakar

Large Language Models (LLMs) such as ChatGPT, have gained significant attention due to their impressive natural language processing capabilities. It is crucial to prioritize human-centered principles when utilizing these models.…

Computation and Language · Computer Science 2023-06-21 Yue Huang , Qihui Zhang , Philip S. Y , Lichao Sun

Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can…

Computation and Language · Computer Science 2024-07-16 Isabel O. Gallegos , Ryan A. Rossi , Joe Barrow , Md Mehrab Tanjim , Sungchul Kim , Franck Dernoncourt , Tong Yu , Ruiyi Zhang , Nesreen K. Ahmed

In this paper, we explore the feasibility of leveraging large language models (LLMs) to automate or otherwise assist human raters with identifying harmful content including hate speech, harassment, violent extremism, and election…

Although large language models (LLMs) have advanced the state-of-the-art in NLP significantly, deploying them for downstream applications is still challenging due to cost, responsiveness, control, or concerns around privacy and security. As…

Computation and Language · Computer Science 2023-11-01 Dong-Ho Lee , Jay Pujara , Mohit Sewak , Ryen W. White , Sujay Kumar Jauhar

Previous work adopts large language models (LLMs) as evaluators to evaluate natural language process (NLP) tasks. However, certain shortcomings, e.g., fairness, scope, and accuracy, persist for current LLM evaluators. To analyze whether…

Computation and Language · Computer Science 2025-01-22 Qintong Li , Leyang Cui , Lingpeng Kong , Wei Bi

Transformer-based language models are able to generate fluent text and be efficiently adapted across various natural language generation tasks. However, language models that are pretrained on large unlabeled web text corpora have been shown…

Computation and Language · Computer Science 2022-07-28 Farshid Faal , Ketra Schmitt , Jia Yuan Yu

Machine Learning (ML) is increasingly applied in real-life scenarios, raising concerns about bias in automatic decision making. We focus on bias as a notion of opinion exclusion, that stems from the direct application of traditional ML…

Machine Learning · Computer Science 2019-11-07 Agathe Balayn , Alessandro Bozzon

Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics. However, the likelihood, a measure of LLM's plausibility for a sentence, can vary due to superficial differences in sentences,…

Computation and Language · Computer Science 2025-11-11 Masanari Oi , Masahiro Kaneko , Ryuto Koike , Mengsay Loem , Naoaki Okazaki

Large language models (LLMs) have become ubiquitous, thus it is important to understand their risks and limitations. Smaller LLMs can be deployed where compute resources are constrained, such as edge devices, but with different propensity…

Computation and Language · Computer Science 2025-04-22 Berk Atil , Vipul Gupta , Sarkar Snigdha Sarathi Das , Rebecca J. Passonneau