# Leveraging Multiple Teachers for Test-Time Adaptation of Language-Guided Classifiers

arXiv: https://arxiv.org/abs/2311.07538 · HTML: https://mlsanity.com/paper/2311.07538/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 13 Nov 2023.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [Demystifying Prompts in Language Models via Perplexity Estimation](https://mlsanity.com/paper/2212.04037/) (2022)
- [Training Complex Models with Multi-Task Weak Supervision](https://mlsanity.com/paper/1810.02840/) (2018)
- [Learning with Latent Language](https://mlsanity.com/paper/1711.00482/) (2017)
- [SITA: Single Image Test-time Adaptation](https://mlsanity.com/paper/2112.02355/) (2021)
- [Training Classifiers with Natural Language Explanations](https://mlsanity.com/paper/1805.03818/) (2018)
- [ExpBERT: Representation Engineering with Natural Language Explanations](https://mlsanity.com/paper/2005.01932/) (2020)
- [Test time Adaptation through Perturbation Robustness](https://mlsanity.com/paper/2110.10232/) (2021)
- [Teaching Machine Comprehension with Compositional Explanations](https://mlsanity.com/paper/2005.00806/) (2020)
- [Self-Supervised Test-Time Learning for Reading Comprehension](https://mlsanity.com/paper/2103.11263/) (2021)
- [Learning from Explanations with Neural Execution Tree](https://mlsanity.com/paper/1911.01352/) (2019)
- [CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations](https://mlsanity.com/paper/2204.07142/) (2022)

## Built on by (most cited first, 2 of 2)

- [Are LLMs Good Annotators for Discourse-level Event Relation Extraction?](https://mlsanity.com/paper/2407.19568/) (2024)
- [LegalCore: A Dataset for Event Coreference Resolution in Legal Documents](https://mlsanity.com/paper/2502.12509/) (2025)

## Abstract (arXiv)

Recent approaches have explored language-guided classifiers capable of classifying examples from novel tasks when provided with task-specific natural language explanations, instructions or prompts (Sanh et al., 2022; R. Menon et al., 2022). While these classifiers can generalize in zero-shot settings, their task performance often varies substantially between different language explanations in unpredictable ways (Lu et al., 2022; Gonen et al., 2022). Also, current approaches fail to leverage unlabeled examples that may be available in many scenarios. Here, we introduce TALC, a framework that uses data programming to adapt a language-guided classifier for a new task during inference when provided with explanations from multiple teachers and unlabeled test examples. Our results show that TALC consistently outperforms a competitive baseline from prior work by an impressive 9.3% (relative improvement). Further, we demonstrate the robustness of TALC to variations in the quality and quantity of provided explanations, highlighting its potential in scenarios where learning from multiple teachers or a crowd is involved. Our code is available at: https://github.com/WeiKangda/TALC.git.