Views
No views yet
LLaMA 3.1 8B Instruct, specifically trained to classify the toxicity level of Spanish-language user comments on news articles. It distinguishes between tow categories:1[
2 {
3 "role": "system",
4 "content": "You are an expert in detecting toxicity in comments, and your goal is to classify comments based on their level of toxicity. The comments were made on news articles. The toxicity categories are:
5 Toxic: Comments that contain derogatory or pejorative language, inappropriate jokes, fearmongering, denial of facts, threats, personal attacks, insults, degradation, or racist or sexist language. Only classify a comment as “toxic” if it contains clear attack language, direct insults, or demeaning references.
6 Non-toxic: Neutral or critical comments that do not include Toxic or Slightly toxic elements. Note that negative or critical comments (those with a serious or discontented tone) are Not toxic or Slightly toxic unless they meet the criteria of the categories above.
7 Please write the corresponding category immediately after the word 'answer.' In case of doubt between two labels, choose the one with the lowest or no toxicity level."
8 },
9 {
10 "role": "user",
11 "content": "Text: "Narco-Bolivarian Communism"
12 },
13 {
14 "role": "assistant",
15 "content": "Toxic"
16 }
17]| Non-toxic | Toxic | |
|---|---|---|
| Non-toxic | 534 | 53 |
| Toxic | 136 | 245 |
| Class | Precision | Recall | F1-score | Support |
|---|---|---|---|---|
| Non-toxic | 0.8222 | 0.6430 | 0.7216 | 587 |
| Toxic | 0.7970 | 0.9097 | 0.8496 | 381 |
| Accuracy | 0.8048 | 968 | ||
| Macro avg | 0.8096 | 0.7764 | 0.7856 | 968 |
| Weighted avg | 0.8069 | 0.8048 | 0.7993 | 968 |
0.7856