Papers with ranking performance

4 papers
Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to generate relevance labels for large language models have not been successful in generating relevance labels.
Approach: They propose a method to combine LLM relevance labels with ranking abilities . they take both LLM generated relevance labels and pairwise preferences .
Outcome: The proposed method balances the ranking and labeling abilities of large language models . it takes both LLM generated relevance labels and pairwise preferences .
MatRank: Text Re-ranking by Latent Preference Matrix (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for text ranking have improved performance, but there are still challenges.
Approach: They propose a method that learns to re-rank the text retrieved for a given query by learning to predict the most relevant passage based on a latent preference matrix.
Outcome: The proposed method outperforms all prior methods on datasets with extensive results.
Similar Region Search using LLMs on Spatial Feature Space (2026.findings-eacl)

Copied to clipboard

Challenge: Existing similarity search methods fail to capture contextual richness of spatial data . existing methods fail in capturing regional characteristics, authors say .
Approach: They propose a similar region search framework that ranks candidate regions based on their similarity to a query region using large language models.
Outcome: The proposed similar region search framework outperforms state-of-the-art methods on real-world city datasets.
Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have led to an influx of AI-generated content on the internet, transforming corpus of Information Retrieval (IR) systems from human-written to a coexistence with LLM-generated contents.
Approach: They propose a benchmark named Cocktail that compares IR models with LLMs to find relevant documents and passages from a corpus.
Outcome: The proposed benchmark aims to evaluate IR models in the mixed-sourced data landscape of the LLM era.

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