Challenge: Existing approaches passively rely on first-stage dense retrievers, which leads to two limitations: failing to retrieve relevant passages in semantically distinct clusters and failing to propagate relevance signals to the broader corpus.
Approach: They propose a framework that propagates sparse LLM relevance signals across the embedding space to guide global exploration.
Outcome: Experiments show that the proposed framework outperforms existing approaches under the same budget on all four datasets.

Similar Papers

REALM: Recursive Relevance Modeling for LLM-based Document Re-Ranking (2025.emnlp-main)

Copied to clipboard

Challenge: Existing LLMs face ranking uncertainty, unstable top-k recovery, and high token cost due to token-intensive prompting.
Approach: They propose a re-ranking framework that captures uncertainty and refines LLM-derived relevance through recursive Bayesian updates.
Outcome: The proposed framework outperforms state-of-the-art re-rankers while reducing token usage and latency.
Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval (2024.acl-long)

Copied to clipboard

Challenge: Dense retrieval requires discriminative embeddings to represent the semantic relationship between query and document.
Approach: They propose an unsupervised approach that performs unsupervised adaptation of large language models for dense retrieval.
Outcome: The proposed model improves on a variety of dense retrieval benchmarks and is available on github.
Multimodal Item Scoring for Natural Language Recommendation via Gaussian Process Regression with LLM Relevance Judgments (2026.findings-acl)

Copied to clipboard

Challenge: Existing NLRec approaches use Dense Retrieval to compute item relevance scores . DR views the request as the sole relevance label, leading to a weak proxy for query relevance.
Approach: They propose to use Gaussian Process Regression to model item relevance . they propose to combine LLM with a Gauss-based kernel to model multimodal relevance judging .
Outcome: The proposed approach outperforms simpler unimodal kernels and baseline methods by up to 65% on four NLRec datasets and two LLM backbones.
Best Practices for Distilling Large Language Models into BERT for Web Search Ranking (2025.coling-industry)

Copied to clipboard

Challenge: Recent studies have highlighted the potential of Large Language Models (LLMs) as zero-shot relevance rankers.
Approach: They propose to use a ranking loss to transfer ranking knowledge from LLMs to smaller models like BERT.
Outcome: The proposed model has been successfully integrated into a commercial web search engine as of February 2024.
Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs (2025.coling-main)

Copied to clipboard

Challenge: Large language models (LLMs) excel in diverse applications but still struggle with non-Latin scripts and low-resource languages.
Approach: They propose a dynamic learning approach that optimizes prompt strategy, embedding model, and LLM per query at runtime.
Outcome: The proposed approach achieves 10-15% improvements in multilingual performance over pre-trained models and 4x gains compared to fine-tuned, language-specific models.
From Selection to Generation: A Survey of LLM-based Active Learning (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been used for selection and training of data for active learning.
Approach: They propose an intuitive taxonomy that categorizes LLM-based active learning techniques and discuss the transformative roles they can play in the active learning loop.
Outcome: The proposed model can generate entirely new data instances and provide more cost-effective annotations with fewer labeled data instances.
An Efficient Retrieval-Based Method for Tabular Prediction with LLM (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for tabular prediction rely on extensive pre-training or fine-tuning of LLMs . a retrieval-based approach eliminates the need for training any modules or performing data augmentation .
Approach: They propose a retrieval-based approach that utilizes the powerful capabilities of large language models in representation, comprehension, and inference.
Outcome: The proposed method exhibits strong predictive performance on tabular prediction task, affirming its practicality and effectiveness.
Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Retrieval-augmented large language models excel in various NLP tasks but are not always helpful when the knowledge required is absent in the model.
Approach: They propose to determine whether the model is knowledgeable on a query via inspecting the (contextualized) pre-trained token embeddings of LLMs.
Outcome: Experiments show that the proposed approach performs better than previous approaches on various benchmarks.
CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search (2025.naacl-industry)

Copied to clipboard

Challenge: Relevance modeling between queries and items is a key component of commercial search engines.
Approach: They propose a framework for continual pre-training of LLMs to enhance domain knowledge . they employ queries and multi-field item to jointly pre-train for enhancing domain knowledge.
Outcome: The proposed model achieves convincing performance compared to strong baselines.
Contextual Relevance and Adaptive Sampling for LLM-Based Document Reranking (2026.acl-long)

Copied to clipboard

Challenge: identifying relevant documents for Reasoning-intensive queries remains a challenge . large language models have shown strong performance in zero-shot document reranking .
Approach: They propose a reranking algorithm that estimates contextual relevance by aggregating LLMs' relevance judgments across batches.
Outcome: The proposed algorithm improves nDCG@10 over retrieval and reranking baselines by 15% and 6–21% respectively.

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