# Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following

arXiv: https://arxiv.org/abs/2302.14691 · HTML: https://mlsanity.com/paper/2302.14691/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 28 Feb 2023.

## Builds on (most cited first, 24 of 24)

- [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)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Transformers learn in-context by gradient descent](https://mlsanity.com/paper/2212.07677/) (2022)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [What Can Transformers Learn In-Context? A Case Study of Simple Function Classes](https://mlsanity.com/paper/2208.01066/) (2022)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization](https://mlsanity.com/paper/2212.12017/) (2022)
- [Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters](https://mlsanity.com/paper/2212.10001/) (2022)
- [Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations](https://mlsanity.com/paper/2212.09865/) (2022)

## Built on by (most cited first, 30 of 33)

- [FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets](https://mlsanity.com/paper/2307.10928/) (2023)
- [Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting](https://mlsanity.com/paper/2305.07004/) (2023)
- [The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning](https://mlsanity.com/paper/2305.14045/) (2023)
- [Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era](https://mlsanity.com/paper/2404.11457/) (2024)
- [PolyLM: An Open Source Polyglot Large Language Model](https://mlsanity.com/paper/2307.06018/) (2023)
- [Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning](https://mlsanity.com/paper/2310.03249/) (2023)
- [Interactive Natural Language Processing](https://mlsanity.com/paper/2305.13246/) (2023)
- [The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs](https://mlsanity.com/paper/2506.11094/) (2025)
- [CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics](https://mlsanity.com/paper/2406.15477/) (2024)
- [Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering](https://mlsanity.com/paper/2306.00526/) (2023)
- [MolecularGPT: Open Large Language Model (LLM) for Few-Shot Molecular Property Prediction](https://mlsanity.com/paper/2406.12950/) (2024)
- [Nudging: Inference-time Alignment of LLMs via Guided Decoding](https://mlsanity.com/paper/2410.09300/) (2024)
- [Generative Calibration for In-context Learning](https://mlsanity.com/paper/2310.10266/) (2023)
- [Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack](https://mlsanity.com/paper/2407.16695/) (2024)
- [Causally Reliable Concept Bottleneck Models](https://mlsanity.com/paper/2503.04363/) (2025)
- [From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning](https://mlsanity.com/paper/2304.07995/) (2023)
- [Multi-party Goal Tracking with LLMs: Comparing Pre-training, Fine-tuning, and Prompt Engineering](https://mlsanity.com/paper/2308.15231/) (2023)
- [Fine-tune Language Models to Approximate Unbiased In-context Learning](https://mlsanity.com/paper/2310.03331/) (2023)
- [Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression](https://mlsanity.com/paper/2402.16058/) (2024)
- [Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack](https://mlsanity.com/paper/2410.06491/) (2024)
- [The Few-shot Dilemma: Over-prompting Large Language Models](https://mlsanity.com/paper/2509.13196/) (2025)
- [Challenges Faced by Large Language Models in Solving Multi-Agent Flocking](https://mlsanity.com/paper/2404.04752/) (2024)
- [FsPONER: Few-shot Prompt Optimization for Named Entity Recognition in Domain-specific Scenarios](https://mlsanity.com/paper/2407.08035/) (2024)
- [JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning](https://mlsanity.com/paper/2310.02953/) (2023)
- [How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment](https://mlsanity.com/paper/2406.11474/) (2024)
- [Improving Language Model Reasoning with Self-motivated Learning](https://mlsanity.com/paper/2404.07017/) (2024)
- [Linearly-Interpretable Concept Embedding Models for Text Analysis](https://mlsanity.com/paper/2406.14335/) (2024)
- [Let AI Entertain You: Increasing User Engagement with Generative AI and Rejection Sampling](https://mlsanity.com/paper/2312.12457/) (2023)
- [Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models](https://mlsanity.com/paper/2312.05503/) (2023)
- [Enhancing Clinical Note Generation with ICD-10, Clinical Ontology Knowledge Graphs, and Chain-of-Thought Prompting Using GPT-4](https://mlsanity.com/paper/2512.05256/) (2025)

## Abstract (arXiv)

In this paper, we present our finding that prepending a Task-Agnostic Prefix Prompt (TAPP) to the input improves the instruction-following ability of various Large Language Models (LLMs) during inference. TAPP is different from canonical prompts for LLMs in that it is a fixed prompt prepended to the beginning of every input regardless of the target task for zero-shot generalization. We observe that both base LLMs (i.e. not fine-tuned to follow instructions) and instruction-tuned models benefit from TAPP, resulting in 34.58% and 12.26% improvement on average, respectively. This implies that the instruction-following ability of LLMs can be improved during inference time with a fixed prompt constructed with simple heuristics. We hypothesize that TAPP assists language models to better estimate the output distribution by focusing more on the instruction of the target task during inference. In other words, such ability does not seem to be sufficiently activated in not only base LLMs but also many instruction-fine-tuned LLMs. All experiments are reproducible from https://github.com/seonghyeonye/TAPP.