# Nudging: Inference-time Alignment of LLMs via Guided Decoding

arXiv: https://arxiv.org/abs/2410.09300 · HTML: https://mlsanity.com/paper/2410.09300/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 42 references that are in the map.
- First posted on arXiv 11 Oct 2024.

## Builds on (most cited first, 30 of 34)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [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)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [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)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning](https://mlsanity.com/paper/2312.01552/) (2023)
- [Mitigating Label Biases for In-context Learning](https://mlsanity.com/paper/2305.19148/) (2023)
- [Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model](https://mlsanity.com/paper/2310.09520/) (2023)
- [A Closer Look at the Limitations of Instruction Tuning](https://mlsanity.com/paper/2402.05119/) (2024)

## Built on by (most cited first, 23 of 23)

- [Base Models Know How to Reason, Thinking Models Learn When](https://mlsanity.com/paper/2510.07364/) (2025)
- [Test-Time Alignment via Hypothesis Reweighting](https://mlsanity.com/paper/2412.08812/) (2024)
- [Don't Throw Away Your Pretrained Model](https://mlsanity.com/paper/2510.09913/) (2025)
- [Optimizing Diversity and Quality through Base-Aligned Model Collaboration](https://mlsanity.com/paper/2511.05650/) (2025)
- [Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems](https://mlsanity.com/paper/2602.05176/) (2026)
- [SpecFuse: Ensembling Large Language Models via Next-Segment Prediction](https://mlsanity.com/paper/2412.07380/) (2024)
- [MoCo: A One-Stop Shop for Model Collaboration Research](https://mlsanity.com/paper/2601.21257/) (2026)
- [Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?](https://mlsanity.com/paper/2511.00689/) (2025)
- [Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning](https://mlsanity.com/paper/2603.07445/) (2026)
- [LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety](https://mlsanity.com/paper/2604.12710/) (2026)
- [Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding](https://mlsanity.com/paper/2601.06403/) (2026)
- [MentorCollab: Large-to-Small Inference-Time Mentorship for Concise Reasoning in Language Models](https://mlsanity.com/paper/2602.05307/) (2026)
- [To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending](https://mlsanity.com/paper/2606.11201/) (2026)
- [Kad: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral](https://mlsanity.com/paper/2510.27017/) (2025)
- [The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment](https://mlsanity.com/paper/2604.06377/) (2026)
- [ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing](https://mlsanity.com/paper/2606.12342/) (2026)
- [Beyond Token-Level Guidance: Inference-Time Alignment of Specialized LLMs via Cross-Family Representation Steering](https://mlsanity.com/paper/2608.30319/) (2026)
- [On the Rejection Criterion for Proxy-based Test-time Alignment](https://mlsanity.com/paper/2604.16146/) (2026)
- [Measuring, Localizing, and Ablating Alignment Signatures in LLMs](https://mlsanity.com/paper/2605.30526/) (2026)
- [Gradient-Guided Reward Optimization for Inference-time Alignment](https://mlsanity.com/paper/2606.09635/) (2026)
- [Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models](https://mlsanity.com/paper/2609.00495/) (2026)
- [SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs](https://mlsanity.com/paper/2609.22153/) (2026)
- [DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning](https://mlsanity.com/paper/2610.18862/) (2026)

## Abstract (arXiv)

Large language models (LLMs) require alignment to effectively and safely follow user instructions. This process necessitates training an aligned version for every base model, resulting in significant computational overhead. In this work, we propose NUDGING, a simple, training-free algorithm that aligns any base model at inference time using a small aligned model. NUDGING is motivated by recent findings that alignment primarily alters the model's behavior on a small subset of stylistic tokens (e.g., discourse markers). We find that base models are significantly more uncertain when generating these tokens. Building on this insight, NUDGING employs a small aligned model to generate nudging tokens to guide the base model's output during decoding when the base model's uncertainty is high, with only a minor additional inference overhead. We evaluate NUDGING across 3 model families on a diverse range of open-instruction tasks. Without any training, nudging a large base model with a 7x-14x smaller aligned model achieves zero-shot performance comparable to, and sometimes surpassing, that of large aligned models. By operating at the token level, NUDGING enables off-the-shelf collaboration between model families. For instance, nudging Gemma-2-27b with Llama-27b-chat outperforms Llama-2-70b-chat on various tasks. Overall, our work offers a modular and cost-efficient solution to LLM alignment. Our code and demo are available at: https://fywalter.github.io/nudging/ .