Do Stochastic Parrots have Feelings Too? Improving Neural Detection of Synthetic Text via Emotion Recognition (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in generative AI have shone a spotlight on high-performance synthetic text generation technologies. |
| Approach: | They propose to use emotion-driven pretrained language models to generate synthetic text that lacks emotional coherence. |
| Outcome: | The proposed detector achieves significant improvements across a range of synthetic text generators, various sized models, datasets, and domains. |
Similar Papers
Through the Looking Glass: Learning to Attribute Synthetic Text Generated by Language Models (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent advances in natural language processing have enabled synthetic text generation that is often comparable to the organic text. |
| Approach: | They propose and test several ML-based methods to attribute authorship of synthetic text to language models (LMs) they propose to use a fine-tuned version of XLNet to achieve excellent accuracy . |
| Outcome: | The proposed method achieves excellent accuracy (91% to near perfect 98%) across a range of experiments where the synthetic text may be generated using pre-trained LMs, fine-tuned LM, or by varying text generation parameters. |
Misery Loves Complexity: Exploring Linguistic Complexity in the Context of Emotion Detection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a negative emotion is a cognitive bias that affects how we express thoughts and opinions online . a recent study shows that negative words generate more engagement and clicks than positive ones . |
| Approach: | They propose to use readability and linguistic complexity metrics to better understand emotions . they propose to fine-tune three state-of-the-art transformers to detect emotions based on a dataset . |
| Outcome: | The proposed model fails to predict emotions on complex texts, the authors show . they also show that more advanced models fail to predict complex texts . |
A Comprehensive Analysis of Preprocessing for Word Representation Learning in Affective Tasks (2020.acl-main)
Copied to clipboard
| Challenge: | Affective tasks such as sentiment analysis, emotion classification and sarcasm detection have enjoyed great popularity in recent years. |
| Approach: | They conduct a comprehensive analysis of the role of preprocessing techniques in affective analysis based on word vector models. |
| Outcome: | The proposed model is the first of its kind and provides useful insights on the role of each preprocessing technique when applied at the training phase, commonly ignored in pretrained word vector models, and/or at the downstream task phase. |
Generative Error Correction for Emotion-aware Speech-to-text Translation (2025.findings-acl)
Copied to clipboard
| Challenge: | Despite recent advances in speech-to-text translation, the impact of the emotion content has been overlooked. |
| Approach: | They propose to use generative error correction (GER) to generate the translation based on the decoded N-best hypotheses and combine emotion and sentiment labels into the LLM finetuning process to enable the model to consider the emotion content. |
| Outcome: | The proposed model can translate speech in English-Chinese using GER and emotion and sentiment labels. |
MojiTalk: Generating Emotional Responses at Scale (P18-1)
Copied to clipboard
| Challenge: | Existing studies on emotion-generating systems focus on small sets of labeled datasets. |
| Approach: | They propose to leverage Twitter data that are naturally labeled with emojis to generate emotional responses. |
| Outcome: | The proposed models can generate high-quality conversation responses in accordance with designated emotions. |
When Words Smile: Generating Diverse Emotional Facial Expressions from Text (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing systems that generate only coarse facial expressions ignore the rich and dynamic nature of face-to-face communication. |
| Approach: | They propose an end-to-end text-to expression model that explicitly focuses on emotional dynamics. |
| Outcome: | The proposed model outperforms baselines on 15,000 text–3D expression pairs on a large-scale dataset. |
Modelling Context Emotions using Multi-task Learning for Emotion Controlled Dialog Generation (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent research has tackled this task using neural generative methods by augmenting emotion classes with the input sequences. |
| Approach: | They propose to use a self-attention based encoder and a decoder with dot product attention mechanism to generate a viable response with a specified emotion. |
| Outcome: | The proposed model outperforms baselines on automatic evaluation measures such as F1 and BLEU scores, thus resulting in more fluent and adequate responses. |
Exploring the Limitations of Detecting Machine-Generated Text (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in the quality of the generation of text by large language models have spurred research into identifying machine-generated text. |
| Approach: | They audit classification performance for detecting machine-generated text by evaluating on texts with varying writing styles. |
| Outcome: | The proposed methods are highly sensitive to stylistic changes and complexity, and in some cases degrade entirely to random classifiers. |
Breaking the Generator Barrier: Disentangled Representation for Generalizable AI-Text Detection (2026.acl-long)
Copied to clipboard
| Challenge: | a rapid proliferation of large language models (LLMs) generate text that increasingly resembles human writing . this makes it difficult to capture subtle cues that distinguish AI-generated content from human-written content . |
| Approach: | They propose a framework that disentangles AI-detection semantics from generator-aware artifacts by latent encoding and perturbation-based regularization. |
| Outcome: | The proposed framework disentangles AI-detection semantics from generator-aware artifacts on 20 representative LLMs across 7 categories. |
Adapting a Language Model for Controlled Affective Text Generation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing models for affective text generation fail to capture emotional aspects of conversations without explicit affective information. |
| Approach: | They propose to incorporate emotion as prior for the probabilistic state-of-the-art text generation model such as GPT-2 and incorporate emotion into the model to ensure grammatical correctness. |
| Outcome: | The proposed model outperforms existing models in all intensities and is robust to human evaluations. |