Pith. sign in

REVIEW 8 cited by

Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.06117 v2 pith:UM2YPTSV submitted 2023-10-09 cs.LG cs.AIcs.CL

classification cs.LGcs.AIcs.CL
keywords promptingreasoningstep-backconceptsllmsmodelspalm-2lperformance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present Step-Back Prompting, a simple prompting technique that enables LLMs to do abstractions to derive high-level concepts and first principles from instances containing specific details. Using the concepts and principles to guide reasoning, LLMs significantly improve their abilities in following a correct reasoning path towards the solution. We conduct experiments of Step-Back Prompting with PaLM-2L, GPT-4 and Llama2-70B models, and observe substantial performance gains on various challenging reasoning-intensive tasks including STEM, Knowledge QA, and Multi-Hop Reasoning. For instance, Step-Back Prompting improves PaLM-2L performance on MMLU (Physics and Chemistry) by 7% and 11% respectively, TimeQA by 27%, and MuSiQue by 7%.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 23 citations worldwide. Full citation record

  1. Training Language Models to Cooperate with Inference-Time Controllers

    cs.AI 2026-07 conditional novelty 6.5 of 10

    Multi-controller post-training with turn-level GRPO over reusable reasoning modules improves LLM transfer to held-out and shifted inference-time controllers versus single-controller RL.

  2. Orchestration for Domain-specific Edge-Cloud Language Models

    cs.DB 2025-07 conditional novelty 6.0 of 10

    ECO-LLM jointly selects query processing, retrieval, and model components per query, cutting cost by 60% and latency up to 6x versus model routing in edge-cloud tests.

  3. Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks

    cs.SE 2025-06 conditional novelty 6.0 of 10

    Across ten software engineering tasks and four LLMs, no prompting technique wins consistently; ES-KNN is best on many tasks, some techniques underperform the baseline, and USC is best for code QA and code generation.

  4. Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning

    cs.CL 2025-09 conditional novelty 5.0 of 10

    An interactive chain-of-thought editor with prune and graft interventions reports large accuracy gains, but without error bars, code, or a comparison to existing editing tools.

  5. Prompt Engineering for Requirements Engineering: A Literature Review and Roadmap

    cs.SE 2025-07 conditional novelty 5.0 of 10

    The first roadmap-oriented systematic literature review of prompt engineering for requirements engineering analyzes 35 studies and proposes a hybrid taxonomy and research roadmap.

  6. PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability

    cs.CV 2025-09 reject novelty 4.0 of 10

    A framework paper that claims its VulnGuard prompt technique cuts harmful LLM outputs by 25-30% via theoretical bounds, without a real proof or empirical test.

  7. Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies

    cs.CL 2025-07 reject novelty 4.0 of 10

    MoR fine-tunes Qwen2.5 on GPT-4o-selected reasoning templates, claiming up to 13.5% accuracy gains, but the reported gains are not robustly supported.

  8. Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion

    cs.IR 2025-06 conditional novelty 4.0 of 10

    Exp4Fuse improves sparse retrieval by fusing the ranked lists from the original query and an LLM-expanded query using a modified reciprocal rank fusion.

Pith tools