mlsanityData to 14 Oct 2026

AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation

arXiv 2402.10646 ↗First posted 16 Feb 2024cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study. Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored. In this work, we design the framework AbsInstruct to enhance LLMs' abstraction ability through instruction tuning. The framework builds instructions with in-depth explanations to assist LLMs in capturing the underlying rationale of abstraction. Meanwhile, we introduce a plausibility estimator to select instructions that are more consistent with the abstraction knowledge of LLMs to be aligned. Then, our framework combines abstraction instructions with general-purpose ones to build a hybrid dataset. Extensive experiments and analyses demonstrate that our framework can considerably enhance LLMs' abstraction ability with strong generalization performance while maintaining their general instruction-following abilities.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 51 of its 100 references that are in the map. First posted on arXiv 16 Feb 2024.

Builds on

51 of 100 references.

References · 51

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  9. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  10. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  11. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  12. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
38 more
  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  3. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  4. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  5. 2023LIMA: Less Is More for Alignmentcited by 1,100
  6. 2018XNLI: Evaluating Cross-lingual Sentence Representationscited by 915
  7. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 868
  8. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 763
  9. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  10. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 699
  11. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 318
  12. 2023Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Modelscited by 243
  13. 2018Constituency Parsing with a Self-Attentive Encodercited by 199
  14. 2023Orca 2: Teaching Small Language Models How to Reasoncited by 159
  15. 2018Multilingual Constituency Parsing with Self-Attention and Pre-Trainingcited by 117
  16. 2019ASER: A Large-scale Eventuality Knowledge Graphcited by 89
  17. 2019GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledgecited by 79
  18. 2023Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Modelscited by 50
  19. 2023Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuningcited by 49
  20. 2024Efficient Tool Use with Chain-of-Abstraction Reasoningcited by 33
  21. 2021ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualitiescited by 28
  22. 2024SciMMIR: Benchmarking Scientific Multi-modal Information Retrievalcited by 23
  23. 2023COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspectivecited by 22
  24. 2019Probabilistic Models of Relational Implicationcited by 17
  25. 2022Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualizationcited by 17
  26. 2023AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graphcited by 17
  27. 2023LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigmscited by 14
  28. 2020Joint Reasoning for Multi-Faceted Commonsense Knowledgecited by 12
  29. 2022Entailment Graph Learning with Textual Entailment and Soft Transitivitycited by 11
  30. 2021Multivalent Entailment Graphs for Question Answeringcited by 10
  31. 2022SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controllercited by 10
  32. 2022Smoothing Entailment Graphs with Language Modelscited by 8
  33. 2021Incorporating Temporal Information in Entailment Graph Miningcited by 7
  34. 2022Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Pathscited by 6
  35. 2023A New Dialogue Response Generation Agent for Large Language Models by Asking Questions to Detect User's Intentionscited by 6
  36. 2023Dynamics of Instruction Fine-Tuning for Chinese Large Language Modelscited by 6
  37. 2024ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Basescited by 6
  38. 2018Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inferencecited by 5

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 10; 2025: 4.

14 papers.

Sort:

By area:

  1. 2024GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theorycited by 37
  2. 2024Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpuscited by 32
  3. 2025AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corporacited by 23
  4. 2024Editing Conceptual Knowledge for Large Language Modelscited by 21
  5. 2024ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertaintycited by 10
  6. 2024CodeGraph: Enhancing Graph Reasoning of LLMs with Codecited by 6
  7. 2024DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenescited by 5
  8. 2024Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstractioncited by 4
  9. 2024On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directionscited by 3
  10. 2025Neutralizing Bias in LLM Reasoning using Entailment Graphscited by 3
  11. 2025ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuningcited by 3
  12. 2024KNOWCOMP POKEMON Team at DialAM-2024: A Two-Stage Pipeline for Detecting Relations in Dialogical Argument Miningcited by 2
2 more
  1. 2024A Survey of Query Optimization in Large Language Modelscited by 1
  2. 2025S2LPP: Small-to-Large Prompt Prediction across LLMscited by 0