Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models
- URL: http://arxiv.org/abs/2311.09214v3
- Date: Sun, 7 Apr 2024 19:17:53 GMT
- Title: Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models
- Authors: Weize Liu, Guocong Li, Kai Zhang, Bang Du, Qiyuan Chen, Xuming Hu, Hongxia Xu, Jintai Chen, Jian Wu,
- Abstract summary: Large language models (LLMs) have achieved remarkable advancements in natural language processing.
The massive scale and computational demands of these models present formidable challenges when considering their practical deployment in resource-constrained environments.
- Score: 20.28989820878285
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language models (LLMs) have achieved remarkable advancements in natural language processing. However, the massive scale and computational demands of these models present formidable challenges when considering their practical deployment in resource-constrained environments. While techniques such as chain-of-thought (CoT) distillation have displayed promise in distilling LLMs into small language models (SLMs), there is a risk that distilled SLMs may still inherit flawed reasoning and hallucinations from LLMs. To address these issues, we propose a twofold methodology: First, we introduce a novel method for distilling the self-evaluation capability from LLMs into SLMs, aiming to mitigate the adverse effects of flawed reasoning and hallucinations inherited from LLMs. Second, we advocate for distilling more comprehensive thinking by incorporating multiple distinct CoTs and self-evaluation outputs, to ensure a more thorough and robust knowledge transfer into SLMs. Experiments on three NLP benchmarks demonstrate that our method significantly improves the performance of distilled SLMs, offering a new perspective for developing more effective and efficient SLMs in resource-constrained environments.
Related papers
- Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.
Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.
We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
arXiv Detail & Related papers (2025-02-04T17:26:58Z) - Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
Large language models (LLMs) have significantly improved language understanding and generation capabilities.
LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.
We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
arXiv Detail & Related papers (2024-12-19T18:08:04Z) - Improving Mathematical Reasoning Capabilities of Small Language Models via Feedback-Driven Distillation [15.542737858152053]
Large Language Models (LLMs) demonstrate exceptional reasoning capabilities, often achieving state-of-the-art performance in various tasks.
A promising solution is knowledge distillation, where LLMs transfer reasoning capabilities to Small Language Models (SLMs), enabling wider deployment on low-resource devices.
We propose a Feedback-Driven Distillation (FDD) framework to enhance SLMs' mathematical reasoning capabilities.
arXiv Detail & Related papers (2024-11-22T03:12:39Z) - LLaVA-KD: A Framework of Distilling Multimodal Large Language Models [70.19607283302712]
We propose a novel framework to transfer knowledge from l-MLLM to s-MLLM.
Specifically, we introduce Multimodal Distillation (MDist) to minimize the divergence between the visual-textual output distributions of l-MLLM and s-MLLM.
We also propose a three-stage training scheme to fully exploit the potential of s-MLLM.
arXiv Detail & Related papers (2024-10-21T17:41:28Z) - Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks.
LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning.
We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
arXiv Detail & Related papers (2024-06-20T13:08:09Z) - Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning [68.83624133567213]
We show that most prevalent MLLMs can be easily fooled by the introduction of a presupposition into the question.
We also propose a simple yet effective method, Active Deduction (AD), to encourage the model to actively perform composite deduction.
arXiv Detail & Related papers (2024-04-19T15:53:27Z) - Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing [56.75702900542643]
We introduce AlphaLLM for the self-improvements of Large Language Models.
It integrates Monte Carlo Tree Search (MCTS) with LLMs to establish a self-improving loop.
Our experimental results show that AlphaLLM significantly enhances the performance of LLMs without additional annotations.
arXiv Detail & Related papers (2024-04-18T15:21:34Z) - MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark [41.68821233828375]
This paper introduces a novel benchmark, termed MLLM-as-a-Judge, to assess the ability of MLLMs in assisting judges across diverse modalities.
Our study reveals that, while MLLMs demonstrate remarkable human-like discernment in Pair Comparison, there is a significant divergence from human preferences in Scoring Evaluation and Batch Ranking.
arXiv Detail & Related papers (2024-02-07T12:28:32Z)
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.