Papers by Jon Saad-Falcon
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
Keshav Santhanam, Jon Saad-Falcon, Martin Franz, Omar Khattab, Avi Sil, Radu Florian, Md Arafat Sultan, Salim Roukos, Matei Zaharia, Christopher Potts
| 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
Jon Saad-Falcon, Rajan Pathe Vivek, William Berrios, Nandita Shankar Naik, Matija Franklin, Bertie Vidgen, Amanpreet Singh, Douwe Kiela, Shikib Mehri
| 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
Jon Saad-Falcon, Omar Khattab, Keshav Santhanam, Radu Florian, Martin Franz, Salim Roukos, Avirup Sil, Md Sultan, Christopher Potts
| 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. |