# A Critical Look At Tokenwise Reward-Guided Text Generation

arXiv: https://arxiv.org/abs/2406.07780 · HTML: https://mlsanity.com/paper/2406.07780/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## 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)
- [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)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [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)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [UltraFeedback: Boosting Language Models with Scaled AI Feedback](https://mlsanity.com/paper/2310.01377/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [From r to Q^*: Your Language Model is Secretly a Q-Function](https://mlsanity.com/paper/2404.12358/) (2024)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [Chain of Hindsight Aligns Language Models with Feedback](https://mlsanity.com/paper/2302.02676/) (2023)
- [Offline RL for Natural Language Generation with Implicit Language Q Learning](https://mlsanity.com/paper/2206.11871/) (2022)

## Built on by (most cited first, 12 of 12)

- [AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/2508.14313/) (2025)
- [MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling](https://mlsanity.com/paper/2503.12123/) (2025)
- [Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities](https://mlsanity.com/paper/2507.13158/) (2025)
- [Towards Cost-Effective Reward Guided Text Generation](https://mlsanity.com/paper/2502.04517/) (2025)
- [Controlling Multimodal LLMs via Reward-guided Decoding](https://mlsanity.com/paper/2508.11616/) (2025)
- [Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language Agents](https://mlsanity.com/paper/2502.10732/) (2025)
- [Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance](https://mlsanity.com/paper/2602.10217/) (2026)
- [Safe Inference-Time Alignment via Lagrangian Reward Augmentation](https://mlsanity.com/paper/2607.02781/) (2026)
- [On the Rejection Criterion for Proxy-based Test-time Alignment](https://mlsanity.com/paper/2604.16146/) (2026)
- [Gradient-Guided Reward Optimization for Inference-time Alignment](https://mlsanity.com/paper/2606.09635/) (2026)
- [S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF](https://mlsanity.com/paper/2607.18258/) (2026)
- [Beyond Reference-Based Evaluation: Reward Models for Meta-Evaluation of Grammatical Error Correction](https://mlsanity.com/paper/2609.21231/) (2026)

## Abstract (arXiv)

Large language models (LLMs) can be improved by aligning with human preferences through fine-tuning -- the so-called reinforcement learning from human feedback (RLHF). However, the cost of fine-tuning an LLM is prohibitive for many users. Due to their ability to bypass LLM fine-tuning, prediction-time tokenwise reward-guided text generation (RGTG) methods have recently been proposed. They use a reward model trained on full sequences to score partial sequences during decoding in a bid to steer the generation towards sequences with high rewards. However, these methods have so far been only heuristically motivated and poorly analyzed. In this work, we show that reward models trained on full sequences are not compatible with scoring partial sequences. To alleviate this, we propose to train a Bradley-Terry reward model on partial sequences explicitly, and autoregressively sample from the implied tokenwise policy during decoding. We study the properties of this reward model and the resulting policy: we show that this policy is proportional to the ratio of two distinct RLHF policies. Our simple approach outperforms previous RGTG methods and performs similarly to strong offline baselines without large-scale LLM fine-tuning. Code for our work is available at https://github.com/ahmadrash/PARGS