Papers by Pedro Rodriguez
Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks (2022.acl-demo)
Copied to clipboard
Tristan Thrush, Kushal Tirumala, Anmol Gupta, Max Bartolo, Pedro Rodriguez, Tariq Kane, William Gaviria Rojas, Peter Mattson, Adina Williams, Douwe Kiela
| Challenge: | Open source system for setting up custom NLP tasks aims to lower technical knowledge and effort required for hosting and evaluating state-of-the-art models. |
| Approach: | They propose to integrate Dynatask with Dynabench to simplify benchmarking . they use a dataset to collect and clean data and train and evaluate models . |
| Outcome: | Dynatask is an open source system for setting up custom NLP tasks . it is integrated with Dynabench, a research platform for rethinking benchmarking in AI . |
Evaluation Paradigms in Question Answering (2021.emnlp-main)
Copied to clipboard
| Challenge: | Despite substantial overlap, subtle but significant distinctions exert an outsize influence on research . one paradigm values creating more intelligent QA systems, the other paradigm values building QA system that appeals to users. |
| Approach: | They propose to use the Cranfield and Manchester paradigms to describe research working towards building human-like, intelligent QA systems. |
| Outcome: | The proposed paradigms are based on the findings of two recent studies on question answering (QA) the Cranfield paradigm is not new, but the Manchester paradigm is christened as the most eclectic in QA . |
Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks (2023.findings-eacl)
Copied to clipboard
Pedro Rodriguez, Mahmoud Azab, Becka Silvert, Renato Sanchez, Linzy Labson, Hardik Shah, Seungwhan Moon
| Challenge: | Existing benchmarks for text-to-video retrieval are incomplete, resulting in false negatives . a recent state-of-the-art model gains 25% recall points, but this is not the case for TVR. |
| Approach: | They propose to retire video captioning datasets as TVR benchmarks . they propose to annotate and release additional caption-video pairs to mitigate this flaw . |
| Outcome: | The proposed method fails to accurately reflect reality, despite lack of purpose-built benchmarks. |
Information Seeking in the Spirit of Learning: A Dataset for Conversational Curiosity (2020.emnlp-main)
Copied to clipboard
| Challenge: | Open-ended human learning and information-seeking systems often ignore the user’s pre-existing knowledge. |
| Approach: | They propose to use pre-existing user knowledge to build a model that reproduces human assistant policies and improves over a bert content model by 13 mean reciprocal rank points. |
| Outcome: | The proposed model reproduces human assistant policies and improves over a bert content model by 13 mean reciprocal rank points. |
SIMMC-VR: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive VR Streams (2023.acl-long)
Copied to clipboard
Te-Lin Wu, Satwik Kottur, Andrea Madotto, Mahmoud Azab, Pedro Rodriguez, Babak Damavandi, Nanyun Peng, Seungwhan Moon
| Challenge: | Existing models lack a large-scale benchmark to capture user–assistant interactions . et al., 2022: 145-160. |
| Approach: | They propose a video-grounded task-oriented dialog dataset that captures real-world AI-assisted user scenarios in VR. |
| Outcome: | The proposed dataset captures real-world AI-assisted user scenarios in VR. |
Instruction-tuned Language Models are Better Knowledge Learners (2024.acl-long)
Copied to clipboard
Zhengbao Jiang, Zhiqing Sun, Weijia Shi, Pedro Rodriguez, Chunting Zhou, Graham Neubig, Xi Lin, Wen-tau Yih, Srini Iyer
| Challenge: | Large language models store factual knowledge in parameters, but it can become outdated as the work evolves . pre-instruction-tuning improves ability of LLMs to absorb knowledge from new documents . |
| Approach: | They propose a method that instruction-tunes on questions prior to training on documents . they propose to use QA pairs to update factual knowledge of large language models . |
| Outcome: | The proposed method outperforms instruction-tuning on documents by 17.8%. |
Byte Latent Transformer: Patches Scale Better Than Tokens (2025.acl-long)
Copied to clipboard
Artidoro Pagnoni, Ramakanth Pasunuru, Pedro Rodriguez, John Nguyen, Benjamin Muller, Margaret Li, Chunting Zhou, Lili Yu, Jason E Weston, Luke Zettlemoyer, Gargi Ghosh, Mike Lewis, Ari Holtzman, Srini Iyer
| Challenge: | Existing large language models (LLMs) are trained on bytes, except for tokenization, which groups bytes into a static set of tokens. |
| Approach: | They propose a new byte-level LLM architecture that encodes bytes into dynamically sized patches, which serve as the primary units of computation. |
| Outcome: | The proposed architecture matches tokenization-based models with improvements in inference efficiency and robustness. |
Item Response Theory for Natural Language Processing (2024.eacl-tutorials)
Copied to clipboard
| Challenge: | This tutorial introduces the wider NLP community to Item Response Theory (IRT) existing software for fitting IRT models is limited by human-data sized constraints. |
| Approach: | They will introduce IRT and the mathematical foundations which make IRT models. |
| Outcome: | This tutorial aims to introduce the wider NLP community to Item Response Theory and show its benefits for a number of NLP tasks. |
Pathologies of Neural Models Make Interpretations Difficult (D18-1)
Copied to clipboard
| Challenge: | Existing methods for NLP use input reduction to determine a word's importance . human accuracy degrades when shown the reduced examples instead of the original . |
| Approach: | They propose a process that iteratively removes the least important word from an input . they show human models make the same predictions with high confidence . |
| Outcome: | The proposed methods expose pathological behaviors of neural models . human experiments show that reduced examples lack information to support the prediction of any label . |
Reimagining Retrieval Augmented Language Models for Answering Queries (2023.findings-acl)
Copied to clipboard
Wang-Chiew Tan, Yuliang Li, Pedro Rodriguez, Richard James, Xi Victoria Lin, Alon Halevy, Wen-tau Yih
| Challenge: | Large language models (LLMs) are expensive to train, deploy, and maintain, both financially and in terms of environmental impact. |
| Approach: | They present a reality check on large language models and compare their predictions to retrieval-augmented language models. |
| Outcome: | The proposed models fare better on question answering tasks and have become the foundation of impressive demos like Chat-GPT. |
Evaluation Examples are not Equally Informative: How should that change NLP Leaderboards? (2021.acl-long)
Copied to clipboard
| Challenge: | Rather than replacing leaderboards, we advocate a re-imagining of the model to highlight if and where progress is made. |
| Approach: | They propose a Bayesian leaderboard model where latent subject skill and latent item difficulty predict correct responses. |
| Outcome: | The proposed model can guide what to annotate, identify annotation errors, detect overfitting, and identify informative examples. |