Papers with Language Modeling

5 papers
Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation (2024.acl-long)

Copied to clipboard

Challenge: Existing studies show that LLMs face challenges in effectively using retrieved information . authors propose a method that considers LLM as "Information Refiner"
Approach: They propose a method that considers LLMs as "Information Refiners" they propose INFO-RAG, which is low-cost and general across various tasks .
Outcome: The proposed method improves performance of LLaMA2 by 9.39% relative points . it is low-cost and general across various tasks, and is robust and in-context learning is possible .
uniblock: Scoring and Filtering Corpus with Unicode Block Information (D19-1)

Copied to clipboard

Challenge: Existing methods to remove sentences consisting of illegal characters are tedious and repetitive.
Approach: They propose a statistical method to identify illegal characters in natural language processing . they use a fixed-size feature vector to generate a Gaussian mixture model for each sentence .
Outcome: The proposed method can score sentences and filter corpus on clean corpus and improve performance.
FQuAD2.0: French Question Answering and Learning When You Don’t Know (2022.lrec-1)

Copied to clipboard

Challenge: Question Answering, including Reading Comprehension, has seen significant scientific breakthroughs over the past few years . but most of these breakthroughs are centered on the English language .
Approach: They propose a dataset to train Question Answering models in the French language . they extend the dataset to 17,000+ unanswerable questions annotated adversarially .
Outcome: The proposed dataset makes it possible to train French Question Answering models with the ability to distinguish unanswerable questions from answerable ones.
MOSAICo: a Multilingual Open-text Semantically Annotated Interlinked Corpus (2024.naacl-long)

Copied to clipboard

Challenge: Existing approaches to integrate semantics into Natural Language Understanding (NLP) systems are cost-effective and environmental impact-related.
Approach: They propose to provide semantically-annotated corpora for four NLU tasks across five languages and to drop the requirement of closed datasets.
Outcome: The proposed model provides hundreds of millions of silver yet high-quality annotations for four NLU tasks across five languages.
Minority Positive Sampling for Switching Points - an Anecdote for the Code-Mixing Language Modeling (2020.lrec-1)

Copied to clipboard

Challenge: Multilingual people code-mix using English phonetic typing and insertion of anglicisms in their native language.
Approach: They propose to use minority positive sampling to selectively induce more sample to achieve better performance.
Outcome: The proposed model performs better than other models, but switching points are the main challenge .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations