# Contrastive Instruction Tuning

arXiv: https://arxiv.org/abs/2402.11138 · HTML: https://mlsanity.com/paper/2402.11138/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 60 references that are in the map.
- First posted on arXiv 17 Feb 2024.

## Builds on (most cited first, 30 of 35)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [Exploring the Limits of Out-of-Distribution Detection](https://mlsanity.com/paper/2106.03004/) (2021)
- [Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models](https://mlsanity.com/paper/2111.02840/) (2021)
- [PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts](https://mlsanity.com/paper/2306.04528/) (2023)
- [Contrastive Training for Improved Out-of-Distribution Detection](https://mlsanity.com/paper/2007.05566/) (2020)
- [BRIO: Bringing Order to Abstractive Summarization](https://mlsanity.com/paper/2203.16804/) (2022)
- [Controllable Natural Language Generation with Contrastive Prefixes](https://mlsanity.com/paper/2202.13257/) (2022)
- [Evaluating the Zero-shot Robustness of Instruction-tuned Language Models](https://mlsanity.com/paper/2306.11270/) (2023)

## Built on by (most cited first, 17 of 17)

- [reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs](https://mlsanity.com/paper/2503.11751/) (2025)
- [RobustFlow: Towards Robust Agentic Workflow Generation](https://mlsanity.com/paper/2509.21834/) (2025)
- [Refine Knowledge of Large Language Models via Adaptive Contrastive Learning](https://mlsanity.com/paper/2502.07184/) (2025)
- [MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks](https://mlsanity.com/paper/2507.19634/) (2025)
- [RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability](https://mlsanity.com/paper/2510.22710/) (2025)
- [Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following](https://mlsanity.com/paper/2502.17204/) (2025)
- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (2025)
- [Monotonic Paraphrasing Improves Generalization of Language Model Prompting](https://mlsanity.com/paper/2403.16038/) (2024)
- [Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO](https://mlsanity.com/paper/2603.03314/) (2026)
- [Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs](https://mlsanity.com/paper/2510.14242/) (2025)
- [Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance](https://mlsanity.com/paper/2510.03528/) (2025)
- [Prompting Underestimates LLM Capability for Time Series Classification](https://mlsanity.com/paper/2601.03464/) (2026)
- [CL3DOR: Contrastive Learning for 3D Large Multimodal Models via Odds Ratio on High-Resolution Point Clouds](https://mlsanity.com/paper/2501.03879/) (2025)
- [Waste Not, Want Not; Recycled Gumbel Noise Improves Consistency in Natural Language Generation](https://mlsanity.com/paper/2503.00831/) (2025)
- [SCENIC: Semantic-Conditioned Edge-Aware Neural Framework for Structured IoT Command Generation](https://mlsanity.com/paper/2606.22296/) (2026)
- [Cross-Relational Preference Learning for Better LLM Instruction Following](https://mlsanity.com/paper/2608.29352/) (2026)
- [Prompt-Robust Language Models: Which Training Strategies Work?](https://mlsanity.com/paper/2609.01217/) (2026)

## Abstract (arXiv)

Instruction tuning has been used as a promising approach to improve the performance of large language models (LLMs) on unseen tasks. However, current LLMs exhibit limited robustness to unseen instructions, generating inconsistent outputs when the same instruction is phrased with slightly varied forms or language styles. This behavior indicates LLMs' lack of robustness to textual variations and generalizability to unseen instructions, potentially leading to trustworthiness issues. Accordingly, we propose Contrastive Instruction Tuning, which maximizes the similarity between the hidden representations of semantically equivalent instruction-instance pairs while minimizing the similarity between semantically different ones. To facilitate this approach, we augment the existing FLAN collection by paraphrasing task instructions. Experiments on the PromptBench benchmark show that CoIN consistently improves LLMs' robustness to unseen instructions with variations across character, word, sentence, and semantic levels by an average of +2.5% in accuracy. Code is available at https://github.com/luka-group/CoIN.