# Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions

arXiv: https://arxiv.org/abs/2311.00233 · HTML: https://mlsanity.com/paper/2311.00233/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 57 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Builds on (most cited first, 30 of 42)

- [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)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts](https://mlsanity.com/paper/2202.01279/) (2022)
- [Preference Ranking Optimization for Human Alignment](https://mlsanity.com/paper/2306.17492/) (2023)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Capturing Failures of Large Language Models via Human Cognitive Biases](https://mlsanity.com/paper/2202.12299/) (2022)

## Built on by (most cited first, 24 of 24)

- [Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models](https://mlsanity.com/paper/2408.02032/) (2024)
- [Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models](https://mlsanity.com/paper/2410.03577/) (2024)
- [Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding](https://mlsanity.com/paper/2505.16652/) (2025)
- [Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation](https://mlsanity.com/paper/2407.07412/) (2024)
- [T-REG: Preference Optimization with Token-Level Reward Regularization](https://mlsanity.com/paper/2412.02685/) (2024)
- [Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions](https://mlsanity.com/paper/2406.16743/) (2024)
- [VACoDe: Visual Augmented Contrastive Decoding](https://mlsanity.com/paper/2408.05337/) (2024)
- [CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation](https://mlsanity.com/paper/2508.05534/) (2025)
- [Exploring and Improving Drafts in Blockwise Parallel Decoding](https://mlsanity.com/paper/2404.09221/) (2024)
- [Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding](https://mlsanity.com/paper/2502.13738/) (2025)
- [Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Models](https://mlsanity.com/paper/2505.17061/) (2025)
- [CRoPS: A Training-Free Hallucination Mitigation Framework for Vision-Language Models](https://mlsanity.com/paper/2601.00659/) (2026)
- [GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback](https://mlsanity.com/paper/2604.08553/) (2026)
- [Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation](https://mlsanity.com/paper/2508.02184/) (2025)
- [Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance](https://mlsanity.com/paper/2510.03528/) (2025)
- [SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph Manipulation](https://mlsanity.com/paper/2503.18988/) (2025)
- [Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification](https://mlsanity.com/paper/2603.24058/) (2026)
- [Mitigating the Influence of Distractor Tasks in LMs with Prior-Aware Decoding](https://mlsanity.com/paper/2401.17692/) (2024)
- [GRAD: Graph-Retrieved Adaptive Decoding for Hallucination Mitigation](https://mlsanity.com/paper/2511.03900/) (2025)
- [Financial Instruction Following Evaluation (FIFE)](https://mlsanity.com/paper/2512.08965/) (2025)
- [IntentCoding: Amplifying User Intent in Code Generation](https://mlsanity.com/paper/2602.00066/) (2026)
- [Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering](https://mlsanity.com/paper/2602.06050/) (2026)
- [BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks](https://mlsanity.com/paper/2606.02947/) (2026)
- [DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models](https://mlsanity.com/paper/2607.23944/) (2026)

## Abstract (arXiv)

While instruction-tuned language models have demonstrated impressive zero-shot generalization, these models often struggle to generate accurate responses when faced with instructions that fall outside their training set. This paper presents Instructive Decoding (ID), a simple yet effective approach that augments the efficacy of instruction-tuned models. Specifically, ID adjusts the logits for next-token prediction in a contrastive manner, utilizing predictions generated from a manipulated version of the original instruction, referred to as a noisy instruction. This noisy instruction aims to elicit responses that could diverge from the intended instruction yet remain plausible. We conduct experiments across a spectrum of such noisy instructions, ranging from those that insert semantic noise via random words to others like 'opposite' that elicit the deviated responses. Our approach achieves considerable performance gains across various instruction-tuned models and tasks without necessitating any additional parameter updates. Notably, utilizing 'opposite' as the noisy instruction in ID, which exhibits the maximum divergence from the original instruction, consistently produces the most significant performance gains across multiple models and tasks.