Search Results for author:
Found 20 papers, 12 papers with code
Grounding learning of modifier dynamics: An application to color naming
In addition, we present a model that operates in the HSV color space.
Diverse Adversaries for Mitigating Bias in Training
Adversarial learning can learn fairer and less biased models of language than standard methods.
Learning-based Optoelectronically Innervated Tactile Finger for Rigid-Soft Interactive Grasping
This paper presents a novel design of a soft tactile finger with omni-directional adaptation using multi-channel optical fibers for rigid-soft interactive grasping.
Robotics
Balancing out Bias: Achieving Fairness Through Balanced Training
Group bias in natural language processing tasks manifests as disparities in system error rates across texts authorized by different demographic groups, typically disadvantaging minority groups.
Evaluating Debiasing Techniques for Intersectional Biases
Bias is pervasive in NLP models, motivating the development of automatic debiasing techniques.
Contrastive Learning for Fair Representations
Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes.
Towards Equal Opportunity Fairness through Adversarial Learning
Adversarial training is a common approach for bias mitigation in natural language processing.
fairlib: A Unified Framework for Assessing and Improving Classification Fairness
This paper presents fairlib, an open-source framework for assessing and improving classification fairness.
Optimising Equal Opportunity Fairness in Model Training
Real-world datasets often encode stereotypes and societal biases.
Systematic Evaluation of Predictive Fairness
Mitigating bias in training on biased datasets is an important open problem.
Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP
Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct.
Proprioceptive Learning with Soft Polyhedral Networks
Proprioception is the "sixth sense" that detects limb postures with motor neurons.
Autoencoding a Soft Touch to Learn Grasping from On-land to Underwater
Robots play a critical role as the physical agent of human operators in exploring the ocean.
Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs
With the rapid evolution of large language models (LLMs), new and hard-to-predict harmful capabilities are emerging.
Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
We release two open versions of the model -- the foundation Jais model, and an instruction-tuned Jais-chat variant -- with the aim of promoting research on Arabic LLMs.
Demystifying Instruction Mixing for Fine-tuning Large Language Models
Instruction tuning significantly enhances the performance of large language models (LLMs) across various tasks.
Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents
However, LLMs are optimized for language generation instead of tool use during training or alignment, limiting their effectiveness as agents.
A Chinese Dataset for Evaluating the Safeguards in Large Language Models
Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs, as well as corresponding prompts that can be used to examine the safety mechanisms of LLMs.
Against The Achilles' Heel: A Survey on Red Teaming for Generative Models
Generative models are rapidly gaining popularity and being integrated into everyday applications, raising concerns over their safety issues as various vulnerabilities are exposed.
