mlsanityData to 14 Oct 2026

OPT-R: Exploring the Role of Explanations in Finetuning and Prompting for Reasoning Skills of Large Language Models

arXiv 2305.12001 ↗First posted 19 May 2023cs.CLcited by 5

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

In this paper, we conduct a thorough investigation into the reasoning capabilities of Large Language Models (LLMs), focusing specifically on the Open Pretrained Transformers (OPT) models as a representative of such models. Our study entails finetuning three different sizes of OPT on a carefully curated reasoning corpus, resulting in two sets of finetuned models: OPT-R, finetuned without explanations, and OPT-RE, finetuned with explanations. We then evaluate all models on 57 out-of-domain tasks drawn from the SUPER-NATURALINSTRUCTIONS benchmark, covering 26 distinct reasoning skills, utilizing three prompting techniques. Through a comprehensive grid of 27 configurations and 6,156 test evaluations, we investigate the dimensions of finetuning, prompting, and scale to understand the role of explanations on different reasoning skills. Our findings reveal that having explanations in the fewshot exemplar has no significant impact on the model's performance when the model is finetuned, while positively affecting the non-finetuned counterpart. Moreover, we observe a slight yet consistent increase in classification accuracy as we incorporate explanations during prompting and finetuning, respectively. Finally, we offer insights on which skills benefit the most from incorporating explanations during finetuning and prompting, such as Numerical (+20.4%) and Analogical (+13.9%) reasoning, as well as skills that exhibit negligible or negative effects.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 26 of its 28 references that are in the map. First posted on arXiv 19 May 2023.

Builds on

26 of 28 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb
  2. 2022Towards Reasoning in Large Language Models: A Survey20 Dec
  3. 2022ALERT: Adapting Language Models to Reasoning Tasks16 Dec

Other references · 23

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  7. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  9. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  10. 2022Emergent Abilities of Large Language Modelscited by 2,512
  11. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  12. 2015A large annotated corpus for learning natural language inferencecited by 1,847
11 more
  1. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 868
  2. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  3. 2018CoQA: A Conversational Question Answering Challengecited by 683
  4. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  5. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  6. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  7. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 324
  8. 2020Transformers as Soft Reasoners over Languagecited by 270
  9. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  10. 2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 236
  11. 2022A Review on Language Models as Knowledge Basescited by 157

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 1.

5 papers.

  1. 2024Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Modelscited by 105
  2. 2023Learning by Self-Explainingcited by 17
  3. 2025CLIPPER: Compression enables long-context synthetic data generationcited by 10
  4. 2024Pretrained Generative Language Models as General Learning Frameworks for Sequence-Based Taskscited by 2
  5. 2024A Survey on the Integration of Generative AI for Critical Thinking in Mobile Networkscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning
  2. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  3. 2025Unveiling Reasoning Thresholds in Language Models: Scaling, Fine-Tuning, and Interpretability through Attention Maps
  4. 2022Explanations from Large Language Models Make Small Reasoners Better
  5. 2023Re-Reading Improves Reasoning in Large Language Models
  6. 2023Metacognitive Prompting Improves Understanding in Large Language Models
  7. 2025Reasoning Capabilities and Invariability of Large Language Models
  8. 2026Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models