Lune

ACL Findings2023

Few Shot Rationale Generation using Self-Training with Dual Teachers

Aditya Srikanth Veerubhotla, Lahari Poddar, Jun Yin, György Szarvas, Sharanya Eswaran

Abstract

Self-rationalizing models that also generate a free-text explanation for their predicted labels are an important tool to build trustworthy AI applications. Since generating explanations for annotated labels is a laborious and costly process, recent models rely on large pretrained language models (PLMs) as their backbone and few-shot learning. In this work we explore a self-training approach leveraging both labeled and unlabeled data to further improve few-shot models, under the assumption that neither human written rationales nor annotated task labels are available at scale. We introduce a novel dual-teacher learning framework, which learns two specialized teacher models for task prediction and rationalization using self-training and distills their knowledge into a multi-tasking student model that can jointly generate the task label and rationale. Furthermore, we formulate a new loss function, Masked Label Regularization (MLR) which promotes explanations to be strongly conditioned on predicted labels. Evaluation on three public datasets demonstrate that the proposed methods are effective in modeling task labels and generating faithful rationales.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language? cites ERASER: A Benchmark to Evaluate Rationalized NLP Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on9

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Revisiting Self-Training for Neural Sequence GenerationJunxian He, Jiatao Gu, Jiajun Shen, Marc'Aurelio RanzatoICLR 2020 · 294 citations
  3. Multi-Task Self-Training for Learning General RepresentationsGolnaz Ghiasi, Barret Zoph, Ekin D. Cubuk, Quoc V. Le et al.ICCV 2021 · 119 citations
  4. Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?Peter Hase, Shiyue Zhang, Harry Xie, Mohit BansalEMNLP Findings 2020 · 62 citations
  5. ERASER: A Benchmark to Evaluate Rationalized NLP ModelsJay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, Eric P. Lehman et al.ACL 2020 · 36 citations

Related papers

  1. ZARA: Improving Few-Shot Self-Rationalization for Small Language ModelsWei-Lin Chen, An-Zi Yen, Cheng-Kuang Wu, Hen-Hsen Huang et al.EMNLP Findings 2023 · 5 citations
  2. Self-training with Few-shot RationalizationMeghana Moorthy Bhat, Alessandro Sordoni, Subhabrata MukherjeeEMNLP 2021
  3. Zero-Shot Rationalization by Multi-Task Transfer Learning from Question AnsweringPo-Nien Kung, Tse-Hsuan Yang, Yi-Cheng Chen, Sheng-Siang Yin et al.EMNLP Findings 2020 · 4 citations
  4. Many-Shot In-Context LearningRishabh Agarwal, Avi Singh, Lei Zhang, Bernd Bohnet et al.NeurIPS 2024 · 271 citations
  5. What to Learn, and How: Toward Effective Learning from RationalesSamuel Carton, Surya Kanoria, Chenhao TanACL Findings 2022 · 10 citations
Dusk over the sea between two cliffs drawn in fine vertical lines