Related papers: Fine-Tuning Over Architectural Complexity: Broad-C…
In this work, we investigate several neural network architectures for fine-grained entity type classification. Particularly, we consider extensions to a recently proposed attentive neural architecture and make three key contributions.…
Text-based web agents offer computational efficiency for autonomous web navigation, yet developing robust agents remains challenging due to the noisy and heterogeneous nature of real-world HTML. Standard Supervised Fine-Tuning (SFT)…
Efficient fine-tuning of pre-trained Text-to-Image (T2I) models involves adjusting the model to suit a particular task or dataset while minimizing computational resources and limiting the number of trainable parameters. However, it often…
Domain-specific finetuning is essential for dense retrievers, yet not all training pairs contribute equally to the learning process. We introduce OPERA, a data pruning framework that exploits this heterogeneity to improve both the…
Large-scale sharing of dialogue data is key to advancing the science of teaching and learning, yet rigorous de-identification remains a major barrier. In mathematics tutoring transcripts, numeric expressions frequently resemble structured…
Fine-grained entity typing (FET) aims to deduce specific semantic types of the entity mentions in text. Modern methods for FET mainly focus on learning what a certain type looks like. And few works directly model the type differences, that…
We study clinical Named Entity Recognition (NER) on the CADEC corpus and compare three families of approaches: (i) BERT-style encoders (BERT Base, BioClinicalBERT, RoBERTa-large), (ii) GPT-4o used with few-shot in-context learning (ICL)…
Detecting sensitive data such as Personally Identifiable Information (PII) and Protected Health Information (PHI) is critical for data security platforms. This study evaluates regex-based pattern matching algorithms and exact-match search…
Fine-tuning adapts pretrained networks to new objectives. Whether the resulting depth profile of representational change reflects an intrinsic property of the model or the magnitude of gradient flow has not been tested directly. We measure…
AI-generated text is nowadays produced at scale across domains and heterogeneous generation pipelines, making robustness to distribution shift a central requirement for supervised binary detectors. We train transformer-based detectors on…
Pixel wise image labeling is an interesting and challenging problem with great significance in the computer vision community. In order for a dense labeling algorithm to be able to achieve accurate and precise results, it has to consider the…
One of the most pressing threats to computing systems is software vulnerabilities, which can compromise both hardware and software components. Existing methods for vulnerability detection remain suboptimal. Traditional techniques are both…
Retrieving code functions, classes or files that are relevant in order to solve a given user query, bug report or feature request from large codebases is a fundamental challenge for Large Language Model (LLM)-based coding agents. Agentic…
Fine-tuning is now the primary method for adapting large neural networks, but it also introduces new integrity risks. An untrusted party can insert backdoors, change safety behavior, or overwrite large parts of a model while claiming only…
De-identification of data used for automatic speech recognition modeling is a critical component in protecting privacy, especially in the medical domain. However, simply removing all personally identifiable information (PII) from end-to-end…
We explore efficient strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints. Two approaches are investigated: (1) attaching a classification head to a pretrained…
Dense retrieval models have become a standard for state-of-the-art information retrieval. However, their high-dimensional, high-precision (float32) vector embeddings create significant storage and memory challenges for real-world…
Building Information Modeling (BIM) is essential for managing building data across the entire lifecycle, supporting tasks from design to maintenance. Natural Language Interface (NLI) systems are increasingly explored as user-friendly tools…
Electronic Medical Records (EMRs) contain clinical narrative text that is of great potential value to medical researchers. However, this information is mixed with Personally Identifiable Information (PII) that presents risks to patient and…
Blind Image Quality Assessment (BIQA) aims to evaluate image quality in line with human perception, without reference benchmarks. Currently, deep learning BIQA methods typically depend on using features from high-level tasks for transfer…