English
Related papers

Related papers: Goodtriever: Adaptive Toxicity Mitigation with Ret…

200 papers

Multimodal large language models (MLLMs) have made significant strides by integrating visual and textual modalities. A critical factor in training MLLMs is the quality of image-text pairs within multimodal pretraining datasets. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Han Huang , Yuqi Huo , Zijia Zhao , Haoyu Lu , Shu Wu , Bingning Wang , Qiang Liu , Weipeng Chen , Liang Wang

Large language models (LLMs) fine-tuned for text-retrieval have demonstrated state-of-the-art results across several information retrieval (IR) benchmarks. However, supervised training for improving these models requires numerous labeled…

Information Retrieval · Computer Science 2024-06-24 William Fleshman , Benjamin Van Durme

Content moderation typically combines the efforts of human moderators and machine learning models. However, these systems often rely on data where significant disagreement occurs during moderation, reflecting the subjective nature of…

Computation and Language · Computer Science 2025-09-01 Guillermo Villate-Castillo , Javier Del Ser , Borja Sanz

Current state-of-the-art large language models are effective in generating high-quality text and encapsulating a broad spectrum of world knowledge. These models, however, often hallucinate and lack locally relevant factual data.…

Software Engineering · Computer Science 2024-02-21 Anton Shapkin , Denis Litvinov , Yaroslav Zharov , Egor Bogomolov , Timur Galimzyanov , Timofey Bryksin

Enzyme-reaction retrieval is a fundamental problem in computational biology, underpinning enzyme characterization, reaction mechanism elucidation, and the rational design of metabolic pathways and biocatalysts. As a bidirectional task, it…

Artificial Intelligence · Computer Science 2026-05-26 Yuhang Zhang , Keyan Ding , Peilin Chen , Han Liu , Can Lin , Ruixi Chen , Shiqi Wang , Qi Song

Reinforcement Learning (RL)-based post-training has significantly advanced the complex reasoning capabilities of language models, fostering sophisticated self-reflection processes. However, this ``slow thinking'' paradigm presents a…

Machine Learning · Computer Science 2025-06-24 Xu Wan , Wei Wang , Wenyue Xu , Wotao Yin , Jie Song , Mingyang Sun

Likelihood training and maximization-based decoding result in dull and repetitive generated texts even when using powerful language models (Holtzman et al., 2019). Adding a loss function for regularization was shown to improve text…

Computation and Language · Computer Science 2021-01-13 Evgeny Lagutin , Daniil Gavrilov , Pavel Kalaidin

Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experiments to study this phenomenon. We analyze the impact of…

Computation and Language · Computer Science 2022-03-08 Canwen Xu , Zexue He , Zhankui He , Julian McAuley

Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that…

Computation and Language · Computer Science 2021-04-16 Mounica Maddela , Fernando Alva-Manchego , Wei Xu

This paper focuses on text detoxification, i.e., automatically converting toxic text into non-toxic text. This task contributes to safer and more respectful online communication and can be considered a Text Style Transfer (TST) task, where…

Computation and Language · Computer Science 2024-06-11 Sourabrata Mukherjee , Akanksha Bansal , Atul Kr. Ojha , John P. McCrae , Ondřej Dušek

Toxic interactions during code reviews can undermine teamwork and hinder productivity in software engineering (SE) teams. While prior studies explore toxicity detection and empirical investigation, they lack real-time detoxification tools…

Software Engineering · Computer Science 2026-04-17 MD Awsaf Alam Anindya , Showvik Biswas , Anindya Iqbal , Jaydeb Sarker , Amiangshu Bosu

Knowledge-Editing-based (KE-based) detoxification has emerged as a promising approach for mitigating harmful behaviours in Large Language Models. Existing evaluations, however, largely rely on automatic toxicity classifiers, implicitly…

Computation and Language · Computer Science 2026-02-12 Ming Dong , Shiyi Tang , Ziyan Peng , Guanyi Chen , Tingting He

Text-to-image (T2I) diffusion models have achieved impressive image generation quality and are increasingly fine-tuned for personalized applications. However, these models often inherit unsafe behaviors from toxic pretraining data, raising…

Machine Learning · Computer Science 2025-12-09 Boheng Li , Renjie Gu , Junjie Wang , Leyi Qi , Yiming Li , Run Wang , Zhan Qin , Tianwei Zhang

Interpretability and effectiveness are two essential and indispensable requirements for adopting machine learning methods in reality. In this paper, we propose a knowledge distillation based decision trees extension, dubbed rectified…

Machine Learning · Computer Science 2020-08-24 Yiming Li , Jiawang Bai , Jiawei Li , Xue Yang , Yong Jiang , Shu-Tao Xia

Large language models (LLMs) are increasingly employed for complex multi-step planning tasks, where the tool retrieval (TR) step is crucial for achieving successful outcomes. Two prevalent approaches for TR are single-step retrieval, which…

Information Retrieval · Computer Science 2023-12-19 Raviteja Anantha , Bortik Bandyopadhyay , Anirudh Kashi , Sayantan Mahinder , Andrew W Hill , Srinivas Chappidi

Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability…

Computation and Language · Computer Science 2026-03-05 Yuxiao Lu , Lin Xu , Yang Sun , Wenjun Li , Jie Shi

Automatically extracting effective queries is challenging in information retrieval, especially in toxic content exploration, as such content is likely to be disguised. With the recent achievements in generative Large Language Model (LLM),…

Information Retrieval · Computer Science 2025-02-27 Shaola Ren , Li Ke , Longtao Huang , Dehong Gao , Hui Xue

Instruction-tuned language models (LM) are able to respond to imperative commands, providing a more natural user interface compared to their base counterparts. In this work, we present Promptriever, the first retrieval model able to be…

Information Retrieval · Computer Science 2024-09-18 Orion Weller , Benjamin Van Durme , Dawn Lawrie , Ashwin Paranjape , Yuhao Zhang , Jack Hessel

Language is a deep-rooted means of perpetration of stereotypes and discrimination. Large Language Models (LLMs), now a pervasive technology in our everyday lives, can cause extensive harm when prone to generating toxic responses. The…

Software Engineering · Computer Science 2026-02-06 Simone Corbo , Luca Bancale , Valeria De Gennaro , Livia Lestingi , Vincenzo Scotti , Matteo Camilli

Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches…

Information Retrieval · Computer Science 2024-09-30 Yubao Tang , Ruqing Zhang , Jiafeng Guo , Maarten de Rijke , Wei Chen , Xueqi Cheng