Search Results for author:
Found 16 papers, 10 papers with code
DMix: Adaptive Distance-aware Interpolative Mixup
Interpolation-based regularisation methods such as Mixup, which generate virtual training samples, have proven to be effective for various tasks and modalities. We extend Mixup and propose DMix, an adaptive distance-aware interpolative Mixup that selects samples based on their diversity in the embedding space.
HypMix: Hyperbolic Interpolative Data Augmentation
Interpolation-based regularisation methods for data augmentation have proven to be effective for various tasks and modalities.
DMix: Distance Constrained Interpolative Mixup
Interpolation-based regularisation methods have proven to be effective for various tasks and modalities.
Sequence Mixup for Zero-Shot Cross-Lingual Part-Of-Speech Tagging
There have been efforts in cross-lingual transfer learning for various tasks.
CIAug: Equipping Interpolative Augmentation with Curriculum Learning
CIAug achieves state-of-the-art results over existing interpolative augmentation methods on 10 benchmark datasets across 4 languages in text classification and named-entity recognition tasks.
Too Big to Fool: Resisting Deception in Language Models
Large language models must balance their weight-encoded knowledge with in-context information from prompts to generate accurate responses.
The BrowserGym Ecosystem for Web Agent Research
The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging automation and Large Language Models (LLMs) for web interaction tasks.
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts.
WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
The ability of large language models (LLMs) to mimic human-like intelligence has led to a surge in LLM-based autonomous agents.
ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild
However, existing methods suffer crucial drawbacks across two critical axes affecting the performance of chart representation models: they are trained on data generated from underlying data tables of the charts, ignoring the visual trends and patterns in chart images, and use weakly aligned vision-language backbone models for domain-specific training, limiting their generalizability when encountering charts in the wild.
A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques
Large language models are first pre-trained on trillions of tokens and then instruction-tuned or aligned to specific preferences.
WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
We study the use of large language model-based agents for interacting with software via web browsers.
Self-Influence Guided Data Reweighting for Language Model Pre-training
Once the pre-training corpus has been assembled, all data samples in the corpus are treated with equal importance during LM pre-training.
Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications
Large-scale pre-trained language models have shown outstanding performance in a variety of NLP tasks.
Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations
Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios.
Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
We also introduce a number of state-of-the-art neural models as baselines that utilize image captioning and data-to-text generation techniques to tackle two problem variations: one assumes the underlying data table of the chart is available while the other needs to extract data from chart images.
