Papers by Jon Saad-Falcon

8 papers
PDFTriage: Question Answering over Long, Structured Documents (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing approaches to document QA use a pre-retrieval step to retrieve the relevant context from documents, but this is incongruous with the user's mental model of the document.
Approach: They propose an approach called PDFTriage that enables models to retrieve the context based on either structure or content.
Outcome: The proposed approach can retrieve context based on structure or content across several classes of questions where existing retrieval-augmented LLMs fail.
Embedding Recycling for Language Models (2023.findings-eacl)

Copied to clipboard

Challenge: Existing studies on embedding recycling have not adequately account for overhead costs.
Approach: They propose to reuse contextualized embeddings from previous runs to speed training and inference of future ones.
Outcome: The proposed technique speeds training and inference with no impact on accuracy.
Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking (2023.findings-acl)

Copied to clipboard

Challenge: Neural information retrieval (IR) systems have progressed rapidly in recent years . many IR benchmarks focus on downstream task accuracy, concealing costs incurred .
Approach: They propose to include efficiency considerations on IR benchmarks to help drive progress . eral et al. propose to incorporate query latency and cost budgets into evaluation .
Outcome: a new study shows that the best IR system varies according to how efficiency considerations are chosen and weighed . the proposed benchmarks would allow for more thorough exploration of possible system designs .
LMUNIT: Fine-grained Evaluation with Natural Language Unit Tests (2025.findings-emnlp)

Copied to clipboard

Challenge: Using natural language unit tests, language models are costly and noisy, and automated metrics provide only coarse, difficult-to-interpret signals.
Approach: They propose a paradigm that decomposes response quality into explicit, testable criteria and a unified scoring model, LMUnit, which combines multi-objective training across preferences, direct ratings, and natural language rationales.
Outcome: The proposed paradigm significantly improves inter-annotator agreement and enables more effective LLM development workflows.
UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for information retrieval tasks require large labeled datasets for fine-tuning, but they can experience significant drops in accuracy due to distribution shifts from the training to the target domain.
Approach: They propose a method for using large language models to generate large numbers of synthetic queries cheaply using an expensive LLM.
Outcome: The proposed method boosts zero-shot accuracy in long-tail domains and achieves substantially lower latency than standard reranking methods.
ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction (2022.naacl-main)

Copied to clipboard

Challenge: Neural information retrieval (IR) methods encode queries and documents into single vectors, but late interaction models produce multi-vector representations at the granularity of each token.
Approach: They propose a retrieval method that couples an aggressive residual compression mechanism with a denoised supervision strategy to improve the quality and space footprint of late interaction.
Outcome: The proposed retriever improves quality and space footprint of late interaction models while reducing space footprint by 6–10x.
ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems (2024.naacl-long)

Copied to clipboard

Challenge: Evaluating retrieval-augmented generation systems relies on hand annotations for input queries, passages to retrieve, and responses to generate.
Approach: They propose an automated evaluation framework for retrieval-augmented generation (RAG) ARES fine tunes lightweight LLM judges on synthetically generated queries and answers .
Outcome: The proposed framework evaluates RAG systems using only human annotations . it can be used to improve system understanding and create targeted solutions .
Examining the Ordering of Rhetorical Strategies in Persuasive Requests (2020.findings-emnlp)

Copied to clipboard

Challenge: Numerous studies have been conducted to understand persuasiveness of text, from explorations of rhetoric in presidential campaigns to the impact of a communicator's likability on persuasiveness.
Approach: They use a Variational Autoencoder model to disentangle content and rhetorical strategies in textual requests from a large-scale loan request corpus and visualize interplay between content and strategy through an attentional LSTM that predicts the success of textual request.
Outcome: The proposed model disentangles content and rhetorical strategies in textual requests from a large-scale loan request corpus and visualizes interplay between content and strategy through attentional LSTM that predicts the success rate of textual request.

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