From Detection to Explanation: Effective Learning Strategies for LLMs in Online Abusive Language Research (2025.coling-main)
Copied to clipboard
Chiara Di Bonaventura, Lucia Siciliani, Pierpaolo Basile, Albert Merono Penuela, Barbara McGillivray
| Challenge: | Abusive language detection requires commonsense reasoning, world knowledge and linguistic nuances that evolve over time. |
| Approach: | They propose a knowledge-guided version of Llama-2 instruction fine-tuned for multi-class abusive language detection and explanation generation that mitigates bias and generates explanations that are relevant to the text and coherent with human reasoning. |
| Outcome: | The proposed model mitigates bias and generates explanations that are relevant to the text and coherent with human reasoning, with an average 48.76% better alignment with human judgment. |
Similar Papers
LLM Sensitivity Challenges in Abusive Language Detection: Instruction-Tuned vs. Human Feedback (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies show that instruction-tuned LLMs under-predict positive classes . however, they are overly sensitive and can be applied for abuse detection without fine-tuning . |
| Approach: | They show that instruction-tuned LLMs tend to under-predict positive classes . they also show that label frequency in the prompt helps with the significant over-prediction . |
| Outcome: | The proposed models under-predict positive classes in social media, whereas they are overly sensitive. |
Revisiting Implicitly Abusive Language Detection: Evaluating LLMs in Zero-Shot and Few-Shot Settings (2025.coling-main)
Copied to clipboard
| Challenge: | Current research focuses on explicit abusive language, but subtler forms of IAL remain insufficiently studied. |
| Approach: | They evaluate the models' capabilities in classifying sentences directly as either IAL or benign, and in extracting linguistic features associated with IAL. |
| Outcome: | The proposed models outperform the best previously reported methods in classifying sentences directly as IAL or benign and extracting linguistic features associated with IAL. |
Implicitly Abusive Language – What does it actually look like and why are we not getting there? (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing datasets make learning implicit abuse difficult, argues a new position paper . a lack of work on implicit abuse has limited the effectiveness of automatic detection . |
| Approach: | They argue that existing datasets make learning implicit abuse difficult . they propose a divide-and-conquer strategy to detect implicit abuse . |
| Outcome: | The proposed model could be improved to detect implicit abuse in a dataset with a standardized model. |
How to Solve Few-Shot Abusive Content Detection Using the Data We Actually Have (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing datasets for abusive language detection are expensive and lack of knowledge about the target is a challenge. |
| Approach: | They propose to build models cheaply for a new target label set and/or language, using only a few training examples of the target domain. |
| Outcome: | The proposed model improves monolingually and across languages using existing datasets and only a few-shots of the target domain. |
When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that Large Language Models (LLMs) are susceptible to backdoor attacks, where triggers embedded in poisoned data can maliciously alter LLMs’ behaviors. |
| Approach: | They propose to leverage LLMs' generative capabilities to generate human-readable explanations for their decisions, enabling direct comparisons between explanations of clean and poisoned data. |
| Outcome: | The proposed model produces coherent explanations for clean inputs but logically flawed explanations on poisoned data. |
Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors (2022.acl-long)
Copied to clipboard
| Challenge: | a new study shows that general abusive language classifiers are reliable in detecting explicit abuse but fail to detect more subtle abuses. |
| Approach: | They propose an interpretability technique to quantify the sensitivity of a trained model to new data . they propose a degree of explicitness metric to suggest out-of-domain unlabeled examples . |
| Outcome: | The proposed interpretability technique is useful for predicting the generalizability of the model on new data. |
Unveiling the Implicit Toxicity in Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies focus on probing toxic outputs that can be easily detected with existing toxicity classifiers, but LLMs can generate diverse implicit toxic output that are difficult to detect via simply zero-shot prompting. |
| Approach: | They propose a reinforcement learning based attacking method to induce the implicit toxic outputs in large language models by fine-tuning toxicity classifiers. |
| Outcome: | The proposed method generates implicit toxic outputs that are difficult to detect via zero-shot prompting on five widely-adopted toxicity classifiers. |
A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated capabilities for generating content that could be deemed harmful. |
| Approach: | They conduct a comprehensive analysis of existing studies on jailbreaking LLMs and their defense techniques. |
| Outcome: | The proposed techniques underperform existing white-box attacks and include special tokens significantly affects the likelihood of successful attacks. |
Large Language Models with Reinforcement Learning from Human Feedback Approach for Enhancing Explainable Sexism Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in natural language processing have significantly improved text comprehension. |
| Approach: | They propose a Reinforcement Learning from Human Feedback (RLHF) based fine-tuning framework for sexism detection that leverages contextual learning to understand and apply instructions to new scenarios without additional training. |
| Outcome: | The proposed framework outperforms existing models on three EDOS tasks and scores 0.8681 on binary sexism detection, 0.6829 on category classification of sexists and 0.4722 on task C. |
XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes remains a significant challenge. |
| Approach: | They propose a dataset that includes 24204 instances where each instance interprets the LLM’s reasoning behavior using knowledge graphs and graph attention networks (GAT). |
| Outcome: | The proposed explanation framework reduces hallucinations and improves grounded explanation generation in large language models. |