mlsanityData to 7 Oct 2026

Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions

arXiv 2402.13514 ↗First posted 21 Feb 2024cs.CL cs.AIcited by 30

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Previous research has typically concentrated on leveraging the internal knowledge of Large Language Models (LLMs) to answer known questions (i.e., textitinternal reasoning such as generate-then-read). In contrast, for questions that fall outside their known scope, these models rely on external knowledge retrieval to provide accurate responses (i.e., textitexternal acting such as retrieve-then-read). However, few previous works consider the textitcompositional questions, which consist of several known and unknown sub-questions, necessitating the dynamic combination of previous two methods (i.e., textitinternal reasoning and external acting) to achieve a better trade-off between effectiveness and efficiency. To this end, we introduce a Self Divide-and-Conquer (textittextttSelf-DC) framework, accompanying with the first Compositional unknown Question-Answering dataset (CuQA). This framework enables LLMs to adaptively choose between using internal knowledge and retrieving external knowledge as needed, resulting in a better trade-off between effectiveness and efficiency. Experimental results on two datasets demonstrate that textittextttSelf-DC can achieve comparable or even better performance with much fewer external calls compared with several strong baselines.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 26 of its 33 references that are in the map. First posted on arXiv 21 Feb 2024.

Builds on

26 of 33 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Fact-Checking Complex Claims with Program-Guided Reasoning22 May
  2. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity8 Feb
  3. 2022Measuring and Narrowing the Compositionality Gap in Language Models7 Oct

Other references · 23

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2020Scaling Laws for Neural Language Modelscited by 6,411
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  8. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  9. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  10. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  11. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  12. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
11 more
  1. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  2. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  3. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 273
  4. 2023Do Large Language Models Know What They Don't Know?cited by 238
  5. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 209
  6. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  7. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  8. 2022Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysiscited by 104
  9. 2023Improving Language Models via Plug-and-Play Retrieval Feedbackcited by 87
  10. 2023Self-Knowledge Guided Retrieval Augmentation for Large Language Modelscited by 69
  11. 2023Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMscited by 62

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 13; 2026: 8.

30 papers.

Sort:

By area:

  1. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
  2. 2025SMART: Self-Aware Agent for Tool Overuse Mitigationcited by 52
  3. 2025ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestrationcited by 44
  4. 2024AppBench: Planning of Multiple APIs from Various APPs for Complex User Instructioncited by 24
  5. 2025Position: Agent Should Invoke External Tools ONLY When Epistemically Necessarycited by 22
  6. 2025Automating Steering for Safe Multimodal Large Language Modelscited by 17
  7. 2026Calibrate-Then-Act: Cost-Aware Exploration in LLM Agentscited by 16
  8. 2024CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Controlcited by 13
  9. 2024UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Modelscited by 13
  10. 2025Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challengescited by 12
  11. 2025Query-Level Uncertainty in Large Language Modelscited by 12
  12. 2024Assessing "Implicit" Retrieval Robustness of Large Language Modelscited by 9
18 more
  1. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  2. 2024Unified Active Retrieval for Retrieval Augmented Generationcited by 8
  3. 2025Agentic Knowledgeable Self-awarenesscited by 8
  4. 2025The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillationcited by 7
  5. 2025ToolSpectrum : Towards Personalized Tool Utilization for Large Language Modelscited by 6
  6. 2026The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?cited by 6
  7. 2024SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generationcited by 5
  8. 2026TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAGcited by 5
  9. 2025To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generationcited by 3
  10. 2025DAST: Difficulty-Aware Self-Training on Large Language Modelscited by 3
  11. 2026From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wildcited by 3
  12. 2026Controlling Tool Use with Heading-Specific Activation Steeringcited by 2
  13. 2024Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptabilitycited by 1
  14. 2026When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoningcited by 1
  15. 2026SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gatingcited by 1
  16. 2024MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Modelscited by 0
  17. 2025LightSearcher: Efficient DeepSearch via Experiential Memorycited by 0
  18. 2026Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering
  2. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structures
  3. 2026KnowledgeBerg: Evaluating Systematic Knowledge Coverage and Compositional Reasoning in Large Language Models
  4. 2023ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
  5. 2025The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?
  6. 2023Teaching Smaller Language Models To Generalise To Unseen Compositional Questions
  7. 2025Self-Taught Agentic Long Context Understanding
  8. 2025Self-Questioning Language Models