# Functionality learning through specification instructions

arXiv: https://arxiv.org/abs/2311.08481 · HTML: https://mlsanity.com/paper/2311.08481/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 68 references that are in the map.
- First posted on arXiv 14 Nov 2023.

## Builds on (most cited first, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets](https://mlsanity.com/paper/2106.10328/) (2021)
- [Instruction Induction: From Few Examples to Natural Language Task Descriptions](https://mlsanity.com/paper/2205.10782/) (2022)
- [How Can We Accelerate Progress Towards Human-like Linguistic Generalization?](https://mlsanity.com/paper/2005.00955/) (2020)
- [Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate](https://mlsanity.com/paper/2108.05921/) (2021)
- [Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets](https://mlsanity.com/paper/1904.02668/) (2019)
- [Fixing Model Bugs with Natural Language Patches](https://mlsanity.com/paper/2211.03318/) (2022)
- [Diversify Your Datasets: Analyzing Generalization via Controlled Variance in Adversarial Datasets](https://mlsanity.com/paper/1910.09302/) (2019)

## Abstract (arXiv)

Test suites assess natural language processing models' performance on specific functionalities: cases of interest involving model robustness, fairness, or particular linguistic capabilities. This paper introduces specification instructions: text descriptions specifying fine-grained task-specific behaviors. For each functionality in a suite, we generate an instruction that describes it. We combine the specification instructions to create specification-augmented prompts, which we feed to language models pre-trained on natural instruction data. We conduct experiments to measure how optimizing for some functionalities may negatively impact functionalities that are not covered by the specification set. Our analyses across four tasks and models of diverse sizes and families show that smaller models struggle to follow specification instructions. However, larger models (>~3B params.) can benefit from specifications and -- surprisingly -- even generalize certain desirable behaviors across functionalities.