Stance detection (SD) identifies a text's position towards a target, typically labeled as favor, against, or none. We introduce Open-Target Stance Detection (OTSD), the most realistic task where targets are neither seen during training nor provided as input. We evaluate Large Language Models (LLMs) GPT-4o, GPT-3.5, Llama-3, and Mistral, comparing their performance to the only existing work, Target-Stance Extraction (TSE), which benefits from predefined targets. Unlike TSE, OTSD removes the dependency of a predefined list, making target generation and evaluation more challenging. We also provide a metric for evaluating target quality that correlates well with human judgment. Our experiments reveal that LLMs outperform TSE in target generation when the real target is explicitly and not explicitly mentioned in the text. Likewise, for stance detection, LLMs excel in explicit cases with comparable performance in non-explicit in general.
相關內容
Artificial Intelligence (AI) techniques, especially Large Language Models (LLMs), have started gaining popularity among researchers and software developers for generating source code. However, LLMs have been shown to generate code with quality issues and also incurred copyright/licensing infringements. Therefore, detecting whether a piece of source code is written by humans or AI has become necessary. This study first presents an empirical analysis to investigate the effectiveness of the existing AI detection tools in detecting AI-generated code. The results show that they all perform poorly and lack sufficient generalizability to be practically deployed. Then, to improve the performance of AI-generated code detection, we propose a range of approaches, including fine-tuning the LLMs and machine learning-based classification with static code metrics or code embedding generated from Abstract Syntax Tree (AST). Our best model outperforms state-of-the-art AI-generated code detector (GPTSniffer) and achieves an F1 score of 82.55. We also conduct an ablation study on our best-performing model to investigate the impact of different source code features on its performance.
The generic text preprocessing pipeline, comprising Tokenisation, Normalisation, Stop Words Removal, and Stemming/Lemmatisation, has been implemented in many ontology matching (OM) systems. However, the lack of standardisation in text preprocessing creates diversity in mapping results. In this paper, we investigate the effect of the text preprocessing pipeline on OM tasks at syntactic levels. Our experiments on 8 Ontology Alignment Evaluation Initiative (OAEI) track repositories with 49 distinct alignments indicate: (1) Tokenisation and Normalisation are currently more effective than Stop Words Removal and Stemming/Lemmatisation; and (2) The selection of Lemmatisation and Stemming is task-specific. We recommend standalone Lemmatisation or Stemming with post-hoc corrections. We find that (3) Porter Stemmer and Snowball Stemmer perform better than Lancaster Stemmer; and that (4) Part-of-Speech (POS) Tagging does not help Lemmatisation. To repair less effective Stop Words Removal and Stemming/Lemmatisation used in OM tasks, we propose a novel context-based pipeline repair approach that significantly improves matching correctness and overall matching performance. We also discuss the use of text preprocessing pipeline in the new era of large language models (LLMs).
Rainbow Deep Q-Network (DQN) demonstrated combining multiple independent enhancements could significantly boost a reinforcement learning (RL) agent's performance. In this paper, we present "Beyond The Rainbow" (BTR), a novel algorithm that integrates six improvements from across the RL literature to Rainbow DQN, establishing a new state-of-the-art for RL using a desktop PC, with a human-normalized interquartile mean (IQM) of 7.4 on atari-60. Beyond Atari, we demonstrate BTR's capability to handle complex 3D games, successfully training agents to play Super Mario Galaxy, Mario Kart, and Mortal Kombat with minimal algorithmic changes. Designing BTR with computational efficiency in mind, agents can be trained using a desktop PC on 200 million Atari frames within 12 hours. Additionally, we conduct detailed ablation studies of each component, analzying the performance and impact using numerous measures.
People with speech disabilities may use speech generating devices to facilitate their speech, aka Augmentative and Alternative Communication (AAC) technology. This technology enables practical conversation; however it remains challenging to deliver expressive and timely comments. In this paper, we study how AAC technology can facilitate such speech, through AI powered interfaces. We focus on the least predictable and most high-paced type: humorous comments. We conducted seven qualitative interviews with people with speech disabilities, and performed thematic analysis to gain in-depth insights in usage and challenges of AAC technology, and the role humor plays for them. We designed four simple AI powered interfaces to create humorous comments. In a user study with five participants with speech disabilities, these interfaces allowed us to study how to best support making well-timed humorous comments. We conclude with a discussion of recommendations for interface design based on both studies.
The human brain encodes stimuli from the environment into representations that form a sensory perception of the world. Despite recent advances in understanding visual and auditory perception, olfactory perception remains an under-explored topic in the machine learning community due to the lack of large-scale datasets annotated with labels of human olfactory perception. In this work, we ask the question of whether pre-trained transformer models of chemical structures encode representations that are aligned with human olfactory perception, i.e., can transformers smell like humans? We demonstrate that representations encoded from transformers pre-trained on general chemical structures are highly aligned with human olfactory perception. We use multiple datasets and different types of perceptual representations to show that the representations encoded by transformer models are able to predict: (i) labels associated with odorants provided by experts; (ii) continuous ratings provided by human participants with respect to pre-defined descriptors; and (iii) similarity ratings between odorants provided by human participants. Finally, we evaluate the extent to which this alignment is associated with physicochemical features of odorants known to be relevant for olfactory decoding.
We examine the challenges in ranking multiple treatments based on their estimated effects when using linear regression or its popular double-machine-learning variant, the Partially Linear Model (PLM), in the presence of treatment effect heterogeneity. We demonstrate by example that overlap-weighting performed by linear models like PLM can produce Weighted Average Treatment Effects (WATE) that have rankings that are inconsistent with the rankings of the underlying Average Treatment Effects (ATE). We define this as ranking reversals and derive a necessary and sufficient condition for ranking reversals under the PLM. We conclude with several simulation studies conditions under which ranking reversals occur.
Feature attribution methods are popular in interpretable machine learning. These methods compute the attribution of each input feature to represent its importance, but there is no consensus on the definition of "attribution", leading to many competing methods with little systematic evaluation, complicated in particular by the lack of ground truth attribution. To address this, we propose a dataset modification procedure to induce such ground truth. Using this procedure, we evaluate three common methods: saliency maps, rationales, and attentions. We identify several deficiencies and add new perspectives to the growing body of evidence questioning the correctness and reliability of these methods applied on datasets in the wild. We further discuss possible avenues for remedy and recommend new attribution methods to be tested against ground truth before deployment. The code is available at \url{//github.com/YilunZhou/feature-attribution-evaluation}.
Non-convex optimization is ubiquitous in modern machine learning. Researchers devise non-convex objective functions and optimize them using off-the-shelf optimizers such as stochastic gradient descent and its variants, which leverage the local geometry and update iteratively. Even though solving non-convex functions is NP-hard in the worst case, the optimization quality in practice is often not an issue -- optimizers are largely believed to find approximate global minima. Researchers hypothesize a unified explanation for this intriguing phenomenon: most of the local minima of the practically-used objectives are approximately global minima. We rigorously formalize it for concrete instances of machine learning problems.
Compared with cheap addition operation, multiplication operation is of much higher computation complexity. The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values. In this paper, we present adder networks (AdderNets) to trade these massive multiplications in deep neural networks, especially convolutional neural networks (CNNs), for much cheaper additions to reduce computation costs. In AdderNets, we take the $\ell_1$-norm distance between filters and input feature as the output response. The influence of this new similarity measure on the optimization of neural network have been thoroughly analyzed. To achieve a better performance, we develop a special back-propagation approach for AdderNets by investigating the full-precision gradient. We then propose an adaptive learning rate strategy to enhance the training procedure of AdderNets according to the magnitude of each neuron's gradient. As a result, the proposed AdderNets can achieve 74.9% Top-1 accuracy 91.7% Top-5 accuracy using ResNet-50 on the ImageNet dataset without any multiplication in convolution layer.
Medical image segmentation requires consensus ground truth segmentations to be derived from multiple expert annotations. A novel approach is proposed that obtains consensus segmentations from experts using graph cuts (GC) and semi supervised learning (SSL). Popular approaches use iterative Expectation Maximization (EM) to estimate the final annotation and quantify annotator's performance. Such techniques pose the risk of getting trapped in local minima. We propose a self consistency (SC) score to quantify annotator consistency using low level image features. SSL is used to predict missing annotations by considering global features and local image consistency. The SC score also serves as the penalty cost in a second order Markov random field (MRF) cost function optimized using graph cuts to derive the final consensus label. Graph cut obtains a global maximum without an iterative procedure. Experimental results on synthetic images, real data of Crohn's disease patients and retinal images show our final segmentation to be accurate and more consistent than competing methods.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191