Decoders Laugh as Loud as Encoders
From the dawn of the computer, Allen Turing dreamed of a robot that could communicate using language as a human being. The recent advances in the field of Large Language Models (LLMs) shocked the scientific community when a single model can apply for various natural language processing (NLP) tasks, while the output results are sometimes even better than most human communication skills. Models such as GPT, Claude, Grok, etc. have left their mark on the scientific community. However, it is unclear how much these models understand what they produce, especially in a nuanced theme such as humor. The question of whether computers understand humor is still open (among the decoders, the latest to be checked was GPT-2). We addressed this issue in this paper; we have showed that a fine-tuned decoder (GPT-4o) performed (Mean F1-macro score of 0.85) as well as the best fine-tuned encoder (RoBERTa with a Mean of F1-score 0.86)
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Generative Models for 3D Point Clouds
Point clouds are rich geometric data structures, where their three dimensional structure offers an excellent domain for understanding the representation learning and generative modeling in 3D space. In this work, we aim …
Representation LearningCascade Decoders-Based Autoencoders for Image Reconstruction
Autoencoders are composed of coding and decoding units, hence they hold the inherent potential of high-performance data compression and signal compressed sensing. The main disadvantages of current autoencoders comprise t…
compressed sensingData CompressionImage CompressionImage ReconstructionMTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model
Detecting laughter in video is essential for affective computing and narrative understanding, yet existing approaches treat it as coarse clip-level classification, failing to capture precise temporal boundaries of brief,…
SEDD-PCC: A Single Encoder-Dual Decoder Framework For End-To-End Learned Point Cloud Compression
To encode point clouds containing both geometry and attributes, most learning-based compression schemes treat geometry and attribute coding separately, employing distinct encoders and decoders. This not only increases co…
AttributeDecoderKnowledge DistillationRepresentation LearningInterpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders
Language models increasingly serve as the backbone of text-to-speech (TTS) systems, yet we understand little about the representations they build when text and generated speech tokens share a single residual stream. We t…