Papers with detection models
Darkness can not drive out darkness: Investigating Bias in Hate SpeechDetection Models (2022.acl-srw)
Copied to clipboard
| Challenge: | a recent study shows that machine learning models are biased and they might make the wrong decisions for the wrong reasons. |
| Approach: | They investigate the impact of social bias on the performance of hate speech detection models . they also investigate the causal effect of intersectional bias on models' unfairness . |
| Outcome: | The proposed model is biased and makes the wrong decisions for the wrong reasons. |
CoCoLoFa: A Dataset of News Comments with Common Logical Fallacies Written by LLM-Assisted Crowds (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing algorithms for detecting logical fallacies in texts are expensive and require large-scale labeled datasets. |
| Approach: | They introduce CoCoLoFa, the largest known logical fallacy dataset, with 7,706 comments for 648 news articles labeled for fallacy presence and type. |
| Outcome: | The proposed dataset outperforms state-of-the-art LLMs in fallacy detection and classification. |
Learning from Few Samples: A Novel Approach for High-Quality Malcode Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Intrusion detection systems (IDS) are limited in labeled samples due to scarcity and lack of diversity in malicious samples. |
| Approach: | They propose a semi-supervised framework that integrates Generative Adversarial Networks with Large Language Models to enhance malicious code generation and SQL Injection detection capabilities. |
| Outcome: | The proposed framework enhances malicious code generation and detection capabilities in few-sample learning scenarios. |
RAGulator: Lightweight Out-of-Context Detectors for Grounded Text Generation (2025.emnlp-industry)
Copied to clipboard
| Challenge: | In enterprise settings, Generative AI has received widespread adoption as a tool to uplift employees' productivity. |
| Approach: | They develop lightweight models capable of detecting when LLM-generated text deviates from retrieved source documents semantically. |
| Outcome: | The proposed models outperform open-source alternatives on credit policy and sustainability reports used in the banking industry. |
Identifying Bias in Machine-generated Text Detection (2026.acl-long)
Copied to clipboard
| Challenge: | a growing number of generative AI systems are detecting text generated by a model or written by . humans perform poorly at the detection task, but show no significant biases on the studied attributes. |
| Approach: | They examine gender, race/ethnicity, English-language learner status, and economic status . they find several models tend to classify disadvantaged groups as machine-generated . |
| Outcome: | The proposed models show strong performance but can cause negative impacts . the models classify disadvantaged groups as machine-generated, while economically disadvantaged students' essays are less likely to be classified as machine generated . |
HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter (2025.acl-long)
Copied to clipboard
Manuel Tonneau, Diyi Liu, Niyati Malhotra, Scott A. Hale, Samuel Fraiberger, Victor Orozco-Olvera, Paul Röttger
| Challenge: | Prior work on automated hate speech detection models has been limited due to systematic biases in evaluation datasets and poor performance across geographies. |
| Approach: | They propose to construct a global hate speech dataset representative of social media settings from tweets posted on September 21, 2022. |
| Outcome: | The proposed dataset covers eight languages and four English-speaking countries and covers eight countries where English is the main language on Twitter. |
Adversary-Aware Rumor Detection (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing rumor detection models do not detect malicious attacks, e.g., framing. |
| Approach: | They propose a weighted-edge transformer-graph network and position-aware Adversarial Response Generator to improve the vulnerability of detection models. |
| Outcome: | The proposed framework achieves state-of-the-art on various rumor detection tasks and maintains performance under adversarial learning. |
LLM-GEm: Large Language Model-Guided Prediction of People’s Empathy Levels towards Newspaper Article (2024.findings-eacl)
Copied to clipboard
| Challenge: | Empathy is a key component of human-to-human interactions, and is often overlooked due to the inherent noise in crowdsourced annotations. |
| Approach: | They propose a large language model-guided empathy prediction system that rectifies annotation errors based on defined annotation selection threshold and makes annotations reliable for conventional empathy prediction models. |
| Outcome: | The proposed system rectifies annotation errors based on defined selection threshold and makes the annotations reliable for conventional empathy prediction models, e.g., BERT-based pre-trained language models. |
HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent benchmarks have attempted to identify and explain hate speech but lack the reasoning to supervise detection models. |
| Approach: | They propose a framework that uses large language models to fill in the gaps in hate speech explanations by using existing annotations. |
| Outcome: | The proposed framework outperforms baselines on SBIC and Implicit Hate using model-generated data and improves generalization to unseen datasets. |
Sparse Black-Box Multimodal Attack for Vision-Language Adversary Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing adversarial attacks using imperceptible perturbations are challenging to simulate . e-commerce product restrictions and hate speech monitoring are examples of such attacks . |
| Approach: | They propose a black-box adversarial attack that leverages sparse perturbations to simulate adversarials exhibited by illegal merchants in the black- box scenario. |
| Outcome: | The proposed method outperforms existing attacks and unimodal attacks by treating images and text in discrete space and outperforming existing models. |
Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent research has developed models targeting specific modalities but lacks transferability between formats. |
| Approach: | They conduct extensive experiments using few-shot in-context learning with large language models to explore the transferability of hate speech detection between modalities. |
| Outcome: | The proposed model outperforms vision-language demonstrations in few-shot learning settings. |
SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods (2025.acl-long)
Copied to clipboard
| Challenge: | Existing speech deepfake datasets are limited in scale and diversity, making it challenging to train models that can generalize well to unseen deepfakkes. |
| Approach: | They propose a large-scale speech deepfake dataset that includes over 3 million deepfak samples, totaling more than 3,000 hours of audio, generated using 40 different speech synthesis tools. |
| Outcome: | The proposed dataset includes over 3 million deepfake samples, totaling more than 3,000 hours of audio, generated using 40 different speech synthesis tools. |
Fine-Grained Transfer Learning for Harmful Content Detection through Label-Specific Soft Prompt Tuning (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing detection models are less effective and generalizable due to static data. |
| Approach: | They propose a method that leverages class-specific knowledge to enhance harmful content detection. |
| Outcome: | The proposed method improves harmful content detection across English and German datasets. |
Navigating the Shadows: Unveiling Effective Disturbances for Modern AI Content Detectors (2024.acl-long)
Copied to clipboard
| Challenge: | Recent research indicates that AI-text detection systems lack robustness and struggle to effectively differentiate perturbed texts. |
| Approach: | They propose to evaluate the robustness of current detection systems by using black-box text perturbation methods and adversarial learning experiments. |
| Outcome: | The proposed methods assess the robustness of current detection models across perturbation granularities and the impact of perturbation data augmentation on the robustity of AI-text detectors. |
RedHerring Attack: Testing the Reliability of Attack Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | In response to adversarial text attacks, attack detection models have been proposed and shown to successfully identify text modified by adversaries. |
| Approach: | They propose to modify a text to cause the detection model to predict an attack while keeping the classifier correct. |
| Outcome: | The proposed model drops detection accuracy between 20 - 71 points while maintaining (or improving) classifier accuracy. |
Beyond Detection: A Defend-and-Summarize Strategy for Robust and Interpretable Rumor Analysis on Social Media (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing detection models for rumors detection are poor interpretability and lack the textual content to detect rumors. |
| Approach: | They propose a framework that analyzes the textual content and propagation paths of rumors on social media and provides multi-perspective prediction explanations. |
| Outcome: | The proposed framework defends against malicious attacks and provides prediction explanations on three public datasets. |
A Survey on Natural Language Processing for Fake News Detection (2020.lrec-1)
Copied to clipboard
| Challenge: | Automated fake news detection is a critical but challenging problem in NLP . social media has accelerated the spread of fake news, threatening public safety . |
| Approach: | They describe the challenges involved in fake news detection and describe related tasks . they outline promising research directions and highlight the difference between fake news and related tasks. |
| Outcome: | The proposed models are more fine-grained, detailed, fair, and practical. |
Can Indirect Prompt Injection Attacks Be Detected and Removed? (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have developed various detection mechanisms to protect against prompt injection attacks. |
| Approach: | They investigate the feasibility of detecting and removing indirect prompt injection attacks . they use two methods to evaluate their performance and train detection models . |
| Outcome: | The proposed method is based on a benchmark dataset and is available on github . it evaluates the performance of existing models and open-source detection models . |
K-HATERS: A Hate Speech Detection Corpus in Korean with Target-Specific Ratings (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing datasets on hate speech detection focus on overt forms of hate . however, a majority of these resources are English-centric, focusing on overtones of hate. |
| Approach: | They propose a new corpus for hate speech detection in Korean with target-specific offensiveness ratings that offer a three-point Likert scale. |
| Outcome: | The proposed corpus is the largest offensive language corpus in Korean and offers target-specific ratings on a three-point Likert scale. |
BotPercent: Estimating Bot Populations in Twitter Communities (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to bot detection are agnostic to social environments the bots operate in . however, standard approaches are not a good fit for the social environments they operate in. |
| Approach: | They propose a method that estimates the percentage of Twitter bots given a community . they use Twitter bot detection datasets and feature-, text-, and graph-based models adjusted to a particular community based on Twitter . |
| Outcome: | The proposed method achieves state-of-the-art in community-level Twitter bot detection across balanced and imbalanced class distribution settings. |