Search Results for author:
Found 34 papers, 6 papers with code
FAIRE: Assessing Racial and Gender Bias in AI-Driven Resume Evaluations
In an era where AI-driven hiring is transforming recruitment practices, concerns about fairness and bias have become increasingly important.
CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning
We introduce CLEAR (Contrasting Textual Feedback with Experts and Amateurs for Reasoning), a novel approach to language model reasoning that leverages the strengths of a larger (expert) model and smaller (amateur) model.
Pause-Tuning for Long-Context Comprehension: A Lightweight Approach to LLM Attention Recalibration
LLMs have demonstrated remarkable proficiency in understanding tasks but continue to struggle with long-context comprehension, particularly with content located in the middle of extensive inputs.
Town Hall Debate Prompting: Enhancing Logical Reasoning in LLMs through Multi-Persona Interaction
Debate is a commonly used form of human communication catered towards problem-solving because of its efficiency.
Enhancing Knowledge Distillation for LLMs with Response-Priming Prompting
We find that Ground Truth prompting results in a 55\% performance increase on GSM8K for a distilled Llama 3. 1 8B Instruct compared to the same model distilled without prompting.
Pragmatic Metacognitive Prompting Improves LLM Performance on Sarcasm Detection
Sarcasm detection is a significant challenge in sentiment analysis due to the nuanced and context-dependent nature of verbiage.
Turkey's Earthquakes: Damage Prediction and Feature Significance Using A Multivariate Analysis
Accurate damage prediction is crucial for disaster preparedness and response strategies, particularly given the frequent earthquakes in Turkey.
Evaluating K-Fold Cross Validation for Transformer Based Symbolic Regression Models
Symbolic Regression remains an NP-Hard problem, with extensive research focusing on AI models for this task.
Introducing MAPO: Momentum-Aided Gradient Descent Prompt Optimization
Momentum-Aided Prompt Optimization (MAPO) enhances the efficiency and efficacy of prompt optimization for Large Language Models (LLMs).
A Debate-Driven Experiment on LLM Hallucinations and Accuracy
Large language models (LLMs) have achieved a degree of success in generating coherent and contextually relevant text, yet they remain prone to a significant challenge known as hallucination: producing information that is not substantiated by the input or external knowledge.
ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems
Retrieval-Augmented Generation (RAG) systems using large language models (LLMs) often generate inaccurate responses due to the retrieval of irrelevant or loosely related information.
Medical Imaging Complexity and its Effects on GAN Performance
The proliferation of machine learning models in diverse clinical applications has led to a growing need for high-fidelity, medical image training data.
Spiking Neural Networks as a Controller for Emergent Swarm Agents
To do this, we use evolutionary algorithms to evolve not only the parameters (the weights, biases, and delays) of a spiking neural network, but also its structure.
QIANets: Quantum-Integrated Adaptive Networks for Reduced Latency and Improved Inference Times in CNN Models
Convolutional neural networks (CNNs) have made significant advances in computer vision tasks, yet their high inference times and latency often limit real-world applicability.
A Comparative Study of Translation Bias and Accuracy in Multilingual Large Language Models for Cross-Language Claim Verification
The rise of digital misinformation has heightened interest in using multilingual Large Language Models (LLMs) for fact-checking.
Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting
Standard methods based on this framework aggregate the final decisions of these rationales but fail to utilize the semantic information detailed in the step-by-step reasoning paths.
Fine-Tuning Language Models for Ethical Ambiguity: A Comparative Study of Alignment with Human Responses
Significant improvements were observed after fine-tuning, with notable enhancements in both cross-entropy and Dirichlet scores, particularly in the latter.
NusaMT-7B: Machine Translation for Low-Resource Indonesian Languages with Large Language Models
Large Language Models (LLMs) have demonstrated exceptional promise in translation tasks for high-resource languages.
DiversityMedQA: Assessing Demographic Biases in Medical Diagnosis using Large Language Models
As large language models (LLMs) gain traction in healthcare, concerns about their susceptibility to demographic biases are growing.
Time-series Crime Prediction Across the United States Based on Socioeconomic and Political Factors
Traditional crime prediction techniques are slow and inefficient when generating predictions as crime increases rapidly \cite{r15}.
AAVENUE: Detecting LLM Biases on NLU Tasks in AAVE via a Novel Benchmark
Detecting biases in natural language understanding (NLU) for African American Vernacular English (AAVE) is crucial to developing inclusive natural language processing (NLP) systems.
From Bias to Balance: Detecting Facial Expression Recognition Biases in Large Multimodal Foundation Models
This study addresses the racial biases in facial expression recognition (FER) systems within Large Multimodal Foundation Models (LMFMs).
Facial Expression Recognition
Facial Expression Recognition (FER)
Intraoperative Glioma Segmentation with YOLO + SAM for Improved Accuracy in Tumor Resection
Preoperative Magnetic Resonance Imaging (MRI) images are often ineffective during surgery due to factors such as brain shift, which alters the position of brain structures and tumors.
Enhancing Depression Diagnosis with Chain-of-Thought Prompting
When using AI to detect signs of depressive disorder, AI models habitually draw preemptive conclusions.
Improving Water Quality Time-Series Prediction in Hong Kong using Sentinel-2 MSI Data and Google Earth Engine Cloud Computing
Effective water quality monitoring in coastal regions is crucial due to the progressive deterioration caused by pollution and human activities.
Enhancing Robustness of Human Detection Algorithms in Maritime SAR through Augmented Aerial Images to Simulate Weather Conditions
Through the utilizations of YOLO, we were able to run different weather conditions and lighting from our augmented dataset for training.
Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks
The value of $n$ influences the length of response generated by the model.
Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language Models
Rapidly increasing model scales coupled with steering methods such as chain-of-thought prompting have led to drastic improvements in language model reasoning.
Improving LLM Abilities in Idiomatic Translation
Our research performs translations using two methods: The first method employs the SentenceTransformers model to semantically generate cosine similarity scores between the meanings of the original and target language idioms, selecting the best idiom (Cosine Similarity method).
Atom-by-atom protein generation and beyond with language models
However, they are constrained to generate proteins with only the set of amino acids represented in their vocabulary.
FenceNet: Fine-grained Footwork Recognition in Fencing
FenceNet takes 2D pose data as input and classifies actions using a skeleton-based action recognition approach that incorporates temporal convolutional networks to capture temporal information.
Keeping it Simple: Language Models can learn Complex Molecular Distributions
In this work, we investigate the capacity of simple language models to learn distributions of molecules.
Understanding Childhood Vulnerability in The City of Surrey
Understanding the community conditions that best support universal access and improved childhood outcomes allows ultimately to improve decision-making in the areas of planning and investment across the early stages of childhood development.
