# Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models

arXiv: https://arxiv.org/abs/2401.11725 · HTML: https://mlsanity.com/paper/2401.11725/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 46 references that are in the map.
- First posted on arXiv 22 Jan 2024.

## Builds on (most cited first, 30 of 36)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://mlsanity.com/paper/2309.11235/) (2023)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models](https://mlsanity.com/paper/2306.08018/) (2023)
- [Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves](https://mlsanity.com/paper/2311.04205/) (2023)
- [Hypothesis Search: Inductive Reasoning with Language Models](https://mlsanity.com/paper/2309.05660/) (2023)
- [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022)
- [Rationale-Augmented Ensembles in Language Models](https://mlsanity.com/paper/2207.00747/) (2022)
- [The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain](https://mlsanity.com/paper/2305.07141/) (2023)
- [Cumulative Reasoning with Large Language Models](https://mlsanity.com/paper/2308.04371/) (2023)
- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations](https://mlsanity.com/paper/2305.18354/) (2023)
- [Symbol tuning improves in-context learning in language models](https://mlsanity.com/paper/2305.08298/) (2023)
- [Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners](https://mlsanity.com/paper/2305.14825/) (2023)
- [Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation](https://mlsanity.com/paper/2305.15541/) (2023)
- [Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks](https://mlsanity.com/paper/2311.09247/) (2023)
- [Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models](https://mlsanity.com/paper/2311.09278/) (2023)

## Built on by (most cited first, 4 of 4)

- [The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding](https://mlsanity.com/paper/2502.08946/) (2025)
- [Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation](https://mlsanity.com/paper/2506.02648/) (2025)
- [Understanding LLMs' Fluid Intelligence Deficiency: An Analysis of the ARC Task](https://mlsanity.com/paper/2502.07190/) (2025)
- [System 2 Reasoning for Human-AI Alignment: Generality and Adaptivity via ARC-AGI](https://mlsanity.com/paper/2410.07866/) (2024)

## Abstract (arXiv)

Symbols (or more broadly, non-natural language textual representations) such as numerical sequences, molecular formulas, and table delimiters widely exist, playing important roles in various tasks such as abstract reasoning, chemical property prediction, and table question answering. Despite the impressive natural language comprehension capabilities of large language models (LLMs), their reasoning abilities for symbols remain inadequate, which could attributed to the difference between symbol representations and general natural languages. We propose symbol-to-language (S2L), a tuning-free method that enables large language models to solve symbol-related problems with information expressed in natural language. Specifically, S2L first converts the symbols involved to language-based representations, which can be implemented by prompting LLMs or leveraging external tools, then these language-based representations are integrated into the original problem via direct substitution or concatenation, serving as useful input information for LLMs. We evaluate the S2L method using both API-based (GPT-4, ChatGPT) and open-source (OpenChat) models over eight symbol-related tasks, ranging from symbol-only abstract reasoning to sentiment analysis in social media. Experimental results show that S2L consistently leads to superior performance. For example, by employing S2L for GPT-4, there can be average significant improvements of +21.9% and +9.5% for subtasks in 1D-ARC and Dyck language, respectively. Codes and data are available at https://github.com/THUNLP-MT/symbol2language.