mlsanityData to 14 Oct 2026

Argumentative Reward Learning: Reasoning About Human Preferences

arXiv 2209.14010 ↗First posted 28 Sep 2022cs.AI cs.HC cs.LGcited by 2

On the map: LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF

Abstract (arXiv)

We define a novel neuro-symbolic framework, argumentative reward learning, which combines preference-based argumentation with existing approaches to reinforcement learning from human feedback. Our method improves prior work by generalising human preferences, reducing the burden on the user and increasing the robustness of the reward model. We demonstrate this with a number of experiments.

Key facts. Cited by 2 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 15 of its 25 references that are in the map. First posted on arXiv 28 Sep 2022.

Builds on

15 of 25 references.

Closest ancestors · 3

Same direction, newest first

  1. 2019Fine-Tuning Language Models from Human Preferences18 Sep
  2. 2018Scalable agent alignment via reward modeling: a research direction19 Nov
  3. 2018Reward learning from human preferences and demonstrations in Atari15 Nov

Other references · 12

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2020Learning to summarize from human feedbackcited by 2,588
  4. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  5. 2016Cooperative Inverse Reinforcement Learningcited by 300
  6. 2021Recursively Summarizing Books with Human Feedbackcited by 290
  7. 2018Deep Learning: A Critical Appraisalcited by 217
  8. 2016Learning Language Games through Interactioncited by 43
  9. 2020Visual Concept-Metaconcept Learningcited by 39
  10. 2013On the Acceptability of Arguments in Preference-Based Argumentationcited by 6
  11. 2019Parenting: Safe Reinforcement Learning from Human Inputcited by 6
  12. 2019An Extensible Interactive Interface for Agent Designcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 1.

2 papers.

  1. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 205
  2. 2026Neurosymbolic Learning for Inference-Time Argumentationcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Capturing Individual Human Preferences with Reward Features
  2. 2026A Regret Minimization Framework on Preference Learning in Large Language Models
  3. 2026Causally Robust Reward Learning from Reason-Augmented Preference Feedback
  4. 2025GRAM-R2: Self-Training Generative Foundation Reward Models for Reward Reasoning
  5. 2026Reinforcement Learning from Human Feedback: A Statistical Perspective
  6. 2026In-Context Reward Adaptation for Robust Preference Modeling
  7. 2026Learning Kernel-Based MDPs from Episodic Preferential Feedback
  8. 2026Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback