Timezone: »
An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction. Ideally, rationale extraction should be faithful (reflective of LM's actual behavior) and plausible (convincing to humans), without compromising the LM's (i.e., task model's) task performance. Although attribution algorithms and select-predict pipelines are commonly used in rationale extraction, they both rely on certain heuristics that hinder them from satisfying all three desiderata. In light of this, we propose UNIREX, a flexible learning framework which generalizes rationale extractor optimization as follows: (1) specify architecture for a learned rationale extractor; (2) select explainability objectives (\ie faithfulness and plausibility criteria); and (3) jointly train the task model and rationale extractor on the task using selected objectives. UNIREX enables replacing prior works' heuristic design choices with a generic learned rationale extractor in (1) and optimizing it for all three desiderata in (2)-(3). To facilitate comparison between methods w.r.t. multiple desiderata, we introduce the Normalized Relative Gain (NRG) metric. On five English text classification datasets, our best UNIREX configuration outperforms baselines by an average of 32.9% NRG.Plus, UNIREX rationale extractors' faithfulness can even generalize to unseen datasets and tasks.
Author Information
Aaron Chan (University of Southern California)
Maziar Sanjabi (Meta AI)
Lambert Mathias (Facebook)
Liang Tan (Facebook)
Shaoliang Nie (Facebook)
Xiaochang Peng
Xiang Ren (University of Southern California)
Xiang Ren joined the Department of Computer Science at USC as Assistant Professor in 2018. Previously, he was a visiting researcher at Stanford University. Xiang received his PhD in Computer Science at University of Illinois at Urbana-Champaign (2017), where he was a Google PhD Fellow and a Richard T. Cheng Fellow working with Prof. Jiawei Han. Xiang's research develops data-driven and machine learning methods for turning unstructured text data into machine-actionable structures. Xiang's research has been recognized with several prestigious awards including a Yahoo!-DAIS Research Excellence Award, a Yelp Dataset Challenge award, a C. W. Gear Outstanding Graduate Student Award and a David J. Kuck Outstanding M.S. Thesis Award. Technologies he developed has been transferred to US Army Research Lab, National Institute of Health, Microsoft, Yelp and TripAdvisor.
Hamed Firooz (Facebook)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Spotlight: UNIREX: A Unified Learning Framework for Language Model Rationale Extraction »
Tue. Jul 19th 02:50 -- 02:55 PM Room Room 301 - 303
More from the Same Authors
-
2021 : SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning »
· Aaron Chan · Xiang Ren -
2022 : Towards Better Understanding of Self-Supervised Representations »
Neha Mukund Kalibhat · Kanika Narang · Hamed Firooz · Maziar Sanjabi · Soheil Feizi -
2022 : BARACK: Partially Supervised Group Robustness With Guarantees »
Nimit Sohoni · Maziar Sanjabi · Nicolas Ballas · Aditya Grover · Shaoliang Nie · Hamed Firooz · Christopher Re -
2023 : SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks »
Yuchen Lin · Yicheng Fu · Karina Yang · Prithviraj Ammanabrolu · Faeze Brahman · Shiyu Huang · Chandra Bhagavatula · Yejin Choi · Xiang Ren -
2023 Poster: Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano »
Chuan Guo · Alexandre Sablayrolles · Maziar Sanjabi -
2023 Poster: Identifying Interpretable Subspaces in Image Representations »
Neha Mukund Kalibhat · Shweta Bhardwaj · C. Bayan Bruss · Hamed Firooz · Maziar Sanjabi · Soheil Feizi -
2023 Poster: Text-To-Concept (and Back) via Cross-Model Alignment »
Mazda Moayeri · Keivan Rezaei · Maziar Sanjabi · Soheil Feizi -
2022 Poster: Federated Learning with Partial Model Personalization »
Krishna Pillutla · Kshitiz Malik · Abdel-rahman Mohamed · Michael Rabbat · Maziar Sanjabi · Lin Xiao -
2022 Spotlight: Federated Learning with Partial Model Personalization »
Krishna Pillutla · Kshitiz Malik · Abdel-rahman Mohamed · Michael Rabbat · Maziar Sanjabi · Lin Xiao -
2018 Poster: GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models »
Jiaxuan You · Rex (Zhitao) Ying · Xiang Ren · Will Hamilton · Jure Leskovec -
2018 Oral: GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models »
Jiaxuan You · Rex (Zhitao) Ying · Xiang Ren · Will Hamilton · Jure Leskovec