Search Results for author:
Found 20 papers, 1 papers with code
Take One Step at a Time to Know Incremental Utility of Demonstration: An Analysis on Reranking for Few-Shot In-Context Learning
Unlike the previous work, we introduce a novel labeling method, incremental utility, which estimates how much incremental knowledge is brought into the LLMs by a demonstration.
It's All Relative! -- A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction
Recent developments in large language models (LLMs) have shown promise in their ability to generate synthetic query-document pairs by prompting with as few as 8 demonstrations.
Ambiguity-Aware In-Context Learning with Large Language Models
In-context learning (ICL) i. e. showing LLMs only a few task-specific demonstrations has led to downstream gains with no task-specific fine-tuning required.
Exploring the Viability of Synthetic Query Generation for Relevance Prediction
While our experiments demonstrate that these modifications help improve performance of QGen techniques, we also find that QGen approaches struggle to capture the full nuance of the relevance label space and as a result the generated queries are not faithful to the desired relevance label.
How Does Beam Search improve Span-Level Confidence Estimation in Generative Sequence Labeling?
Sequence labeling is a core task in text understanding for IE/IR systems.
QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation
Thus, in this paper we make the following contributions: (1) We demonstrate that Retrieval Augmentation of queries provides LLMs with valuable additional context enabling improved understanding.
GROOT: Corrective Reward Optimization for Generative Sequential Labeling
GROOT works by training a generative sequential labeling model to match the decoder output distribution with that of the (black-box) reward function.
FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation
Retrieval-augmented generation models offer many benefits over standalone language models: besides a textual answer to a given query they provide provenance items retrieved from an updateable knowledge base.
Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling
This paper studies multi-task training of retrieval-augmented generation models for knowledge-intensive tasks.
Transforming Sequence Tagging Into A Seq2Seq Task
Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks.
Designing biological circuits: from principles to applications
Genetic circuit design is a well-studied problem in synthetic biology.
Effect of Dormant Spare Capacity on the Attack Tolerance of Complex Networks
The vulnerability of networks to targeted attacks is an issue of widespread interest for policymakers, military strategists, network engineers and systems biologists alike.
WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning
First, WIT is the largest multimodal dataset by the number of image-text examples by 3x (at the time of writing).
Ranked #1 on
Image Retrieval
on WIT
The art of molecular computing: whence and whither
An astonishingly diverse biomolecular circuitry orchestrates the functioning machinery underlying every living cell.
Goal directed molecule generation using Monte Carlo Tree Search
One challenging and essential task in biochemistry is the generation of novel molecules with desired properties.
DICT-MLM: Improved Multilingual Pre-Training using Bilingual Dictionaries
In particular, by requiring the model to predict the language-specific token, the MLM objective disincentivizes learning a language-agnostic representation -- which is a key goal of multilingual pre-training.
DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling
Pre-trained models like BERT (Devlin et al., 2018) have dominated NLP / IR applications such as single sentence classification, text pair classification, and question answering.
Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation
The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a single model.
Learning Multilingual Word Embeddings Using Image-Text Data
There has been significant interest recently in learning multilingual word embeddings -- in which semantically similar words across languages have similar embeddings.
Methods for Ordinal Peer Grading
Thus, in this paper we study the problem of automatically inferring student grades from ordinal peer feedback, as opposed to existing methods that require cardinal peer feedback.
