# Predicting Text Preference Via Structured Comparative Reasoning

arXiv: https://arxiv.org/abs/2311.08390 · HTML: https://mlsanity.com/paper/2311.08390/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 14 Nov 2023.

## Placed in

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

## Builds on (most cited first, 27 of 27)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Chain-of-Verification Reduces Hallucination in Large Language Models](https://mlsanity.com/paper/2309.11495/) (2023)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [MathPrompter: Mathematical Reasoning using Large Language Models](https://mlsanity.com/paper/2303.05398/) (2023)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering](https://mlsanity.com/paper/2307.16877/) (2023)
- [Deductive Verification of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2306.03872/) (2023)
- [Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization](https://mlsanity.com/paper/2302.08081/) (2023)
- [Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations](https://mlsanity.com/paper/2307.08678/) (2023)
- [Improving Large Language Model Fine-tuning for Solving Math Problems](https://mlsanity.com/paper/2310.10047/) (2023)
- [Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models](https://mlsanity.com/paper/2311.00287/) (2023)
- [Pre-training Language Models for Comparative Reasoning](https://mlsanity.com/paper/2305.14457/) (2023)

## Built on by (most cited first, 6 of 6)

- [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024)
- [RRM: Robust Reward Model Training Mitigates Reward Hacking](https://mlsanity.com/paper/2409.13156/) (2024)
- [Self-Generated Critiques Boost Reward Modeling for Language Models](https://mlsanity.com/paper/2411.16646/) (2024)
- [CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation](https://mlsanity.com/paper/2410.02748/) (2024)
- [Real-Time Aligned Reward Model beyond Semantics](https://mlsanity.com/paper/2601.22664/) (2026)
- [LAMPO: Large Language Models as Preference Machines for Few-shot Ordinal Classification](https://mlsanity.com/paper/2408.03359/) (2024)

## Abstract (arXiv)

Comparative reasoning plays a crucial role in text preference prediction; however, large language models (LLMs) often demonstrate inconsistencies in their reasoning. While approaches like Chain-of-Thought improve accuracy in many other settings, they struggle to consistently distinguish the similarities and differences of complex texts. We introduce SC, a prompting approach that predicts text preferences by generating structured intermediate comparisons. SC begins by proposing aspects of comparison, followed by generating textual comparisons under each aspect. We select consistent comparisons with a pairwise consistency comparator that ensures each aspect's comparisons clearly distinguish differences between texts, significantly reducing hallucination and improving consistency. Our comprehensive evaluations across various NLP tasks, including summarization, retrieval, and automatic rating, demonstrate that SC equips LLMs to achieve state-of-the-art performance in text preference prediction.