Papers by Dante Everaert

4 papers
Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies have shown that LLMs struggle to identify the boundaries of their own knowledge and tend to prioritize external information over internal knowledge learned during pre-training.
Approach: They conduct a comprehensive analysis of LLM representation behaviors and demonstrate the significance of using representations in knowledge checking.
Outcome: The proposed classifiers improve performance even when dealing with noisy knowledge databases.
Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to personalize large language models (LLMs) rely on heuristic methods to compress user profiles but they ignore how LLMs process and prioritize different profile components.
Approach: They propose an attention-guided context compression framework that leverages attention feedback from a marking model to mark important personalization sentences and guides a compression model to generate task-relevant compressed user contexts.
Outcome: The proposed framework outperforms baselines across tasks, token limits, and settings while reducing token usage by 50 times.
AmazonQAC: A Large-Scale, Naturalistic Query Autocomplete Dataset (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing systems that provide a graphical representation of QAC are limited in their ability to provide real-time data.
Approach: They introduce a new QAC dataset sourced from Amazon Search logs . they assess Prefix Trees, semantic retrieval, and Large Language Models with and without finetuning .
Outcome: The proposed system can predict search terms based on user-typed prefixes . the proposed system achieves only half of what is theoretically possible on the test data .
Retrieval Augmented Spelling Correction for E-Commerce Applications (2024.emnlp-industry)

Copied to clipboard

Challenge: e-commerce spelling correction services face a challenge with new brand names . we propose a new approach that uses a fine-tuned retrieval algorithm to correct for brand names.
Approach: They propose a method that uses product names to be incorporated into a large language model to do contextual spelling correction.
Outcome: The proposed approach improves performance with only minor latency increases . the proposed approach is more efficient than a stand-alone LLM .

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