mlsanityData to 7 Oct 2026

Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models

arXiv 2311.09278 ↗First posted 15 Nov 2023cs.CL cs.AIcited by 38

Not on the map. Why?

Abstract (arXiv)

Although Large Language Models (LLMs) demonstrate remarkable ability in processing and generating human-like text, they do have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language(e.g., chemical molecular formula). Injecting a collection of symbolic data directly into the training of LLMs can be problematic, as it disregards the synergies among different symbolic families and overlooks the need for a balanced mixture of natural and symbolic data. In this work, we tackle these challenges from both a data and framework perspective and introduce Symbol-LLM series models. First, we curated a data collection consisting of 34 tasks and incorporating approximately 20 distinct symbolic families, intending to capture the interrelations and foster synergies between symbols. Then, a two-stage tuning framework succeeds in injecting symbolic knowledge without loss of the generality ability. Extensive experiments on both symbol- and NL-centric tasks demonstrate the balanced and superior performances of Symbol-LLM series models. The project page is https://xufangzhi.github.io/symbol-llm-page/.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 55 of its 80 references that are in the map. First posted on arXiv 15 Nov 2023.

Builds on

55 of 80 references.

References · 55

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  8. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  9. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  10. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  11. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  12. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
38 more
  1. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  2. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  3. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  4. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  5. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  6. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  7. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  8. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  9. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  10. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  11. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
  12. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
  13. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  14. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  15. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 618
  16. 2023Instruction Tuning for Large Language Models: A Surveycited by 617
  17. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  18. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  19. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  20. 2023How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resourcescited by 405
  21. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 379
  22. 2021Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoningcited by 376
  23. 2016Solving General Arithmetic Word Problemscited by 353
  24. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  25. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 314
  26. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 309
  27. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  28. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  29. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
  30. 2020MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmarkcited by 156
  31. 2019SParC: Cross-Domain Semantic Parsing in Contextcited by 141
  32. 2015Large-scale Simple Question Answering with Memory Networkscited by 127
  33. 2018NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating Systemcited by 97
  34. 2020Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsingcited by 72
  35. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaborationcited by 70
  36. 2023Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translationcited by 59
  37. 2019Augmenting Neural Networks with First-order Logiccited by 51
  38. 2023Text2KGBench: A Benchmark for Ontology-Driven Knowledge Graph Generation from Textcited by 48

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 18; 2025: 16; 2026: 3.

38 papers.

Sort:

By area:

  1. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agentscited by 553
  2. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  3. 2025VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Modelscited by 102
  4. 2025PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoningcited by 58
  5. 2024InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignmentcited by 56
  6. 2025Empowering LLMs with Logical Reasoning: A Comprehensive Surveycited by 51
  7. 2024Break the Chain: Large Language Models Can be Shortcut Reasonerscited by 32
  8. 2024EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understandingcited by 32
  9. 2024Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Modelscited by 23
  10. 2024Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Surveycited by 20
  11. 2024From Natural Language to SQL: Review of LLM-based Text-to-SQL Systemscited by 15
  12. 2024Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Modelscited by 13
26 more
  1. 2024Structure Guided Large Language Model for SQL Generationcited by 9
  2. 2024Can Large Language Models Act as Symbolic Reasoners?cited by 8
  3. 2025CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Taskscited by 8
  4. 2023Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognitioncited by 7
  5. 2025JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligencecited by 7
  6. 2024VProChart: Answering Chart Question through Visual Perception Alignment Agent and Programmatic Solution Reasoningcited by 6
  7. 2025GKG-LLM: A Unified Framework for Generalized Knowledge Graph Constructioncited by 6
  8. 2025CellVerse: Do Large Language Models Really Understand Cell Biology?cited by 5
  9. 2025Are LLMs Stable Formal Logic Translators in Logical Reasoning Across Linguistically Diversified Texts?cited by 5
  10. 2024Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Modelscited by 4
  11. 2024A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extractioncited by 4
  12. 2024Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLMcited by 4
  13. 2025Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunitiescited by 4
  14. 2025CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedbackcited by 4
  15. 2025Non-Interactive Symbolic-Aided Chain-of-Thought for Logical Reasoningcited by 4
  16. 2024Logic Agent: Enhancing Validity with Logic Rule Invocationcited by 3
  17. 2024Visual Grounding Methods for Efficient Interaction with Desktop Graphical User Interfacescited by 3
  18. 2025Integrating Expert Knowledge into Logical Programs via LLMscited by 3
  19. 2025Neuro-Symbolic Frameworks: Conceptual Characterization and Empirical Comparative Analysiscited by 2
  20. 2025Exploring Database Normalization Effects on SQL Generationcited by 2
  21. 2024PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answeringcited by 1
  22. 2025Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humanscited by 1
  23. 2026Helix: A Dual-Helix Co-Evolutionary Multi-Agent System for Prompt Optimization and Question Reformulationcited by 1
  24. 2026Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expandingcited by 1
  25. 2025textttSEM-CTRL: Semantically Controlled Decodingcited by 0
  26. 2026LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machinescited by 0