Distilling Mathematical Reasoning Capabilities into Small Language Models

• URL: http://arxiv.org/abs/2401.11864v5
• Date: Thu, 1 Aug 2024 04:03:32 GMT
• Title: Distilling Mathematical Reasoning Capabilities into Small Language Models
• Authors: Xunyu Zhu, Jian Li, Yong Liu, Can Ma, Weiping Wang,
• Abstract summary: This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) We introduce Equation-of-Thought Distillation (EoTD), a novel technique that encapsulates the reasoning process into equation-based representations to construct an EoTD dataset for fine-tuning SLMs.
• Score: 21.768293256849113
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance. We introduce Equation-of-Thought Distillation (EoTD), a novel technique that encapsulates the reasoning process into equation-based representations to construct an EoTD dataset for fine-tuning SLMs. Additionally, we propose the Ensemble Thoughts Distillation (ETD) framework to enhance the reasoning performance of SLMs. This involves creating a reasoning dataset with multiple thought processes, including Chain-of-Thought (CoT), Program-of-Thought (PoT), and Equation-of-Thought (EoT), and using it for fine-tuning. Our experimental performance demonstrates that EoTD significantly boosts the reasoning abilities of SLMs, while ETD enables these models to achieve state-of-the-art reasoning performance.

Related papers

• Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data [53.433309883370974]
  This work explores the potential and limitations of using graph-based synthetic reasoning data as training signals to enhance Large Language Models' reasoning capabilities. Our experiments, conducted on two established natural language reasoning tasks, demonstrate that supervised fine-tuning with synthetic graph-based reasoning data effectively enhances LLMs' reasoning performance without compromising their effectiveness on other standard evaluation benchmarks.
  arXiv  Detail & Related papers  (2024-09-19T03:39:09Z)
• Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning [78.72226641279863]
  Sparse Mixture of Expert (SMoE) models have emerged as a scalable alternative to dense models in language modeling. Our research explores task-specific model pruning to inform decisions about designing SMoE architectures. We introduce an adaptive task-aware pruning technique UNCURL to reduce the number of experts per MoE layer in an offline manner post-training.
  arXiv  Detail & Related papers  (2024-09-02T22:35:03Z)
• Key-Point-Driven Mathematical Reasoning Distillation of Large Language Model [15.542737858152053]
  We propose Key-Point-Driven Mathematical Reasoning Distillation (KPDD) to mitigate misunderstanding errors. KPDD enhances the reasoning performance of SLMs by breaking down the problem-solving process into three stages. Experiments show KPDD-CoT significantly improves reasoning abilities, while KPDD-PoT achieves state-of-the-art performance in mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2024-07-14T11:41:03Z)
• Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models [63.36637269634553]
  We present a novel method of further improving performance by requiring models to compare multiple reasoning chains. We find that instruction tuning on DCoT datasets boosts the performance of even smaller, and therefore more accessible, language models.
  arXiv  Detail & Related papers  (2024-07-03T15:01:18Z)
• Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning [55.265138447400744]
  Statement-Tuning is a technique that models discriminative tasks as a set of finite statements and trains an encoder model to discriminate between the potential statements to determine the label. Experimental results demonstrate that Statement-Tuning achieves competitive performance compared to state-of-the-art LLMs with significantly fewer parameters. The study investigates the impact of several design choices on few-shot and zero-shot generalization, revealing that Statement-Tuning can achieve strong performance with modest training data.
  arXiv  Detail & Related papers  (2024-04-19T14:05:03Z)
• Dual Instruction Tuning with Large Language Models for Mathematical Reasoning [26.00472810721806]
  We propose a dual instruction tuning strategy to model mathematical reasoning from both forward and reverse directions. This involves introducing the Intermediate Reasoning State Prediction task (forward reasoning) and the Instruction Reconstruction task (reverse reasoning) to enhance the LLMs' understanding and execution of instructions. Comprehensive experiments validate the effectiveness and domain generalization of the dual instruction tuning strategy across various mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2024-03-27T06:43:58Z)
• Enhancing Large Language Model with Decomposed Reasoning for Emotion Cause Pair Extraction [13.245873138716044]
  Emotion-Cause Pair Extraction (ECPE) involves extracting clause pairs representing emotions and their causes in a document. Inspired by recent work, we explore leveraging large language model (LLM) to address ECPE task without additional training. We introduce chain-of-thought to mimic human cognitive process and propose the Decomposed Emotion-Cause Chain (DECC) framework.
  arXiv  Detail & Related papers  (2024-01-31T10:20:01Z)
• Guiding Language Model Reasoning with Planning Tokens [122.43639723387516]
  Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks. We propose a hierarchical generation scheme to encourage a more structural generation of chain-of-thought steps. Our approach requires a negligible increase in trainable parameters (0.001%) and can be applied through either full fine-tuning or a more parameter-efficient scheme.
  arXiv  Detail & Related papers  (2023-10-09T13:29:37Z)
• No Train Still Gain. Unleash Mathematical Reasoning of Large Language Models with Monte Carlo Tree Search Guided by Energy Function [3.0299876288833345]
  Large language models (LLMs) demonstrate impressive language understanding and contextual learning abilities. LLMs often struggle to generate correct reasoning steps and answers despite having high probabilities for the solutions. We propose a method that incorporates Monte Carlo Tree Search (MCTS) and a lightweight energy function to rank decision steps.
  arXiv  Detail & Related papers  (2023-09-01T13:10:54Z)
• Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA [5.117094291273979]
  Large Language Models (LLMs) have shown outstanding performance across wide range of downstream tasks. We propose Sci-CoT, a two-stage framework that separates the processes of generating rationales and inferring answers. Our 80-million parameter model is able to exceed the performance of BLOOM-176B in the ARC-Easy dataset under the few shot setting.
  arXiv  Detail & Related papers  (2023-08-09T03:18:07Z)
• MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning [53.90744622542961]
  Reasoning in mathematical domains remains a significant challenge for small language models (LMs) We introduce a new method that exploits existing mathematical problem datasets with diverse annotation styles. Experimental results show that our strategy enables a LLaMA-7B model to outperform prior approaches.
  arXiv  Detail & Related papers  (2023-07-16T05:41:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.