RESPECT: A framework for promoting inclusive and respectful conversations in online communications
Bibliographic record
Abstract
Toxicity and bias in online conversations hinder respectful interactions, leading to issues such as harassment and discrimination. While advancements in natural language processing (NLP) have improved the detection and mitigation of toxicity on digital platforms, the evolving nature of social media conversations demands continuous innovation. Previous efforts have made strides in identifying and reducing toxicity; however, a unified and adaptable framework for managing toxic content across diverse online discourse remains essential. This paper introduces a comprehensive framework R ESPECT designed to effectively identify and mitigate toxicity in online conversations. The framework comprises two components: an encoder-only model for detecting toxicity and a decoder-only model for generating debiased versions of the text. By leveraging the capabilities of transformer-based models, toxicity is addressed as a binary classification problem. Subsequently, open-source and proprietary large language models are utilized through prompt-based approaches to rewrite toxic text into non-toxic, and making sure these are contextually accurate alternatives. Empirical results demonstrate that this approach significantly reduces toxicity across various conversational styles, fostering safer and more respectful communication in online environments. • RESPECT framework identifies toxicity in online discourse. • RESPECT framework use prompt engineering to debias the hateful content. • RESPECT framework classifier and debiaser can be extended to other LLMs.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.018 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.004 | 0.008 |
| Open science | 0.002 | 0.005 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".