# OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models

arXiv: https://arxiv.org/abs/2410.23703 · HTML: https://mlsanity.com/paper/2410.23703/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 36 of its 84 references that are in the map.
- First posted on arXiv 31 Oct 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 36)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [AlignScore: Evaluating Factual Consistency with a Unified Alignment Function](https://mlsanity.com/paper/2305.16739/) (2023)
- [RA-DIT: Retrieval-Augmented Dual Instruction Tuning](https://mlsanity.com/paper/2310.01352/) (2023)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [Multi-Hop Knowledge Graph Reasoning with Reward Shaping](https://mlsanity.com/paper/1808.10568/) (2018)
- [Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering](https://mlsanity.com/paper/2308.13259/) (2023)
- [Training Socially Aligned Language Models on Simulated Social Interactions](https://mlsanity.com/paper/2305.16960/) (2023)
- [RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation](https://mlsanity.com/paper/2403.05313/) (2024)
- [Towards Better Chain-of-Thought Prompting Strategies: A Survey](https://mlsanity.com/paper/2310.04959/) (2023)
- [InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment](https://mlsanity.com/paper/2402.08785/) (2024)
- [Limitations of Autoregressive Models and Their Alternatives](https://mlsanity.com/paper/2010.11939/) (2020)
- [Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs](https://mlsanity.com/paper/2404.15676/) (2024)

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

- [Skill-R1: Agent Skill Evolution via Reinforcement Learning](https://mlsanity.com/paper/2605.09359/) (2026)
- [CTRLS: Chain-of-Thought Reasoning via Latent State-Transition](https://mlsanity.com/paper/2507.08182/) (2025)
- [WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning](https://mlsanity.com/paper/2602.17025/) (2026)
- [Pluralistic Off-policy Evaluation and Alignment](https://mlsanity.com/paper/2509.19333/) (2025)
- [Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning](https://mlsanity.com/paper/2605.02913/) (2026)
- [Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability](https://mlsanity.com/paper/2603.10384/) (2026)
- [OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents](https://mlsanity.com/paper/2605.11169/) (2026)
- [Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck](https://mlsanity.com/paper/2605.08526/) (2026)
- [MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization](https://mlsanity.com/paper/2605.10784/) (2026)
- [Disentangling Deception and Hallucination Failures in LLMs](https://mlsanity.com/paper/2602.14529/) (2026)
- [KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment](https://mlsanity.com/paper/2607.03166/) (2026)
- [OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models](https://mlsanity.com/paper/2609.36264/) (2026)

## Abstract (arXiv)

Offline evaluation of LLMs is crucial in understanding their capacities, though current methods remain underexplored in existing research. In this work, we focus on the offline evaluation of the chain-of-thought capabilities and show how to optimize LLMs based on the proposed evaluation method. To enable offline feedback with rich knowledge and reasoning paths, we use knowledge graphs (e.g., Wikidata5m) to provide feedback on the generated chain of thoughts. Due to the heterogeneity between LLM reasoning and KG structures, direct interaction and feedback from KGs on LLM behavior are challenging, as they require accurate entity linking and grounding of LLM-generated chains of thought in the KG. To address the above challenge, we propose an offline chain-of-thought evaluation framework, OCEAN, which models chain-of-thought reasoning in LLMs as an MDP and evaluate the policy's alignment with KG preference modeling. To overcome the reasoning heterogeneity and grounding problems, we leverage on-policy KG exploration and RL to model a KG policy that generates token-level likelihood distributions for LLM-generated chain-of-thought reasoning paths, simulating KG reasoning preference. Then we incorporate the knowledge-graph feedback on the validity and alignment of the generated reasoning paths into inverse propensity scores and propose KG-IPS estimator. Theoretically, we prove the unbiasedness of the proposed KG-IPS estimator and provide a lower bound on its variance. With the off-policy evaluated value function, we can directly enable off-policy optimization to further enhance chain-of-thought alignment. Our empirical study shows that OCEAN can be efficiently optimized for generating chain-of-thought reasoning paths with higher estimated values without affecting LLMs' general abilities in downstream tasks or their internal knowledge.