Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Page not in menu
This is a page not in th emain menu
Posts
portfolio
publications
Sociocultural knowledge is needed for selection of shots in hate speech detection tasks
arXiv
This paper introduces HATELEXICON, a lexicon of slurs and targets of hate speech for multiple countries, and demonstrates its use in interpreting model predictions.
Hallucination Augmented Recitations for Language Models
arXiv
This paper proposes a novel method using counterfactual open book QA to improve attribution in language models.
Language-Agnostic Bias Detection in Language Models with Bias Probing
EMNLP 2023 Findings
This paper introduces LABDet, a robust and language-agnostic method for evaluating social bias in pretrained language models.
MEAL: Stable and Active Learning for Few-Shot Prompting
EMNLP 2023 Findings
This paper introduces MEAL, a method for stable and active learning in few-shot prompting to address high variance in data selection and run variability.
LongForm: Effective Instruction Tuning with Reverse Instructions
EMNLP 2024 Findings
This paper presents LongForm-C, a dataset created through reverse instructions to enhance instruction tuning for language models.
Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena
arXiv
This paper demonstrates the usefulness of Construction Grammar through Argument Structure Constructions and proposes a hybrid human-LLM approach for corpus construction.
MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory
arXiv
This paper introduces MemLLM, a method for finetuning LLMs to use an explicit read-write memory, addressing limitations in knowledge-intensive tasks.
Consistent Document-Level Relation Extraction via Counterfactuals
EMNLP 2024 Findings
This paper presents CovEReD, a counterfactual data generation approach for document-level relation extraction datasets.
TurkishMMLU: Measuring Massive Multitask Language Understanding in Turkish
EMNLP 2024 Findings
This paper presents TurkishMMLU, the first multitask, multiple-choice QA benchmark designed specifically for Turkish.
SYNTHEVAL: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists
EMNLP 2024 Findings
This paper introduces SYNTHEVAL, a hybrid approach for evaluating NLP models through dynamic behavioral testing.
CRAFT: Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation
Submitted to TACL
This paper proposes CRAFT, a method for generating synthetic datasets for specialized tasks using a few user-written examples.
MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions
Submitted to TACL
This paper introduces MURI, a novel method for generating high-quality instruction tuning datasets for low-resource languages without human annotators.