mlsanityData to 14 Oct 2026

Predicting Text Preference Via Structured Comparative Reasoning

arXiv 2311.08390 ↗First posted 14 Nov 2023cs.CLcited by 6

On the map: LLM reasoning → Reasoning benchmarks and evaluation

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.

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.

Builds on

27 of 50 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Deductive Verification of Chain-of-Thought Reasoning6 Jun
  2. 2023Pre-training Language Models for Comparative Reasoning23 May
  3. 2023PaLM 2 Technical Report17 May
  4. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb

Other references · 23

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  5. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2023Mistral 7Bcited by 3,164
  8. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  9. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  10. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  11. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 625
  12. 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Trainingcited by 401
11 more
  1. 2022News Summarization and Evaluation in the Era of GPT-3cited by 327
  2. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 324
  3. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 307
  4. 2023Faithful Chain-of-Thought Reasoningcited by 288
  5. 2023MathPrompter: Mathematical Reasoning using Large Language Modelscited by 236
  6. 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Biascited by 232
  7. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 151
  8. 2023Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarizationcited by 122
  9. 2023Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanationscited by 85
  10. 2023Improving Large Language Model Fine-tuning for Solving Math Problemscited by 49
  11. 2023Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Modelscited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 0; 2026: 1.

6 papers.

  1. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 269
  2. 2024RRM: Robust Reward Model Training Mitigates Reward Hackingcited by 76
  3. 2024Self-Generated Critiques Boost Reward Modeling for Language Modelscited by 71
  4. 2024CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generationcited by 18
  5. 2026Real-Time Aligned Reward Model beyond Semanticscited by 13
  6. 2024LAMPO: Large Language Models as Preference Machines for Few-shot Ordinal Classificationcited by 5

Similar, not cited

Close in wording, no citation either way

  1. 2025Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes
  2. 2025Estimating the Error of Large Language Models at Pairwise Text Comparison
  3. 2024Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments
  4. 2024Towards a Unified View of Preference Learning for Large Language Models: A Survey
  5. 2025A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models
  6. 2024Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization
  7. 2024Towards Improved Preference Optimization Pipeline: from Data Generation to Budget-Controlled Regularization
  8. 2024Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts