Distilling Reasoning Ability from Large Language Models with Adaptive Thinking

• URL: http://arxiv.org/abs/2404.09170v3
• Date: Sat, 6 Jul 2024 17:41:04 GMT
• Title: Distilling Reasoning Ability from Large Language Models with Adaptive Thinking
• Authors: Xiaoshu Chen, Sihang Zhou, Ke Liang, Xinwang Liu,
• Abstract summary: Chain of thought finetuning (cot-finetuning) aims to endow small language models (SLM) with reasoning ability to improve their performance towards specific tasks. Most existing cot-finetuning methods adopt a pre-thinking mechanism, allowing the SLM to generate a rationale before providing an answer. This mechanism enables SLM to analyze and think about complex questions, but it also makes answer correctness highly sensitive to minor errors in rationale. We propose a robust post-thinking mechanism to generate answers before rationale.
• Score: 54.047761094420174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Chain of thought finetuning (cot-finetuning) aims to endow small language models (SLM) with reasoning ability to improve their performance towards specific tasks by allowing them to imitate the reasoning procedure of large language models (LLM) beyond simply predicting the answers. Most existing cot-finetuning methods adopt a pre-thinking mechanism, allowing the SLM to generate a rationale before providing an answer. This mechanism enables SLM to analyze and think about complex questions, but it also makes answer correctness highly sensitive to minor errors in rationale. Therefore, we propose a robust post-thinking mechanism to generate answers before rationale. Thanks to this answer-first setting, 1) the answer can escape from the adverse effects caused by minor errors in the rationale; 2) the rationale serves as an error amplifier to the answer, which makes the SLM focus on learning hard samples; 3) the inferring efficiency can also benefit from the setting since users can stop the generation right after answers are outputted when inference is conducted. However, although the post-thinking mechanism brings many advantages and improves the overall performance of SLM on specific tasks, it may lose the ability to think about the questions and decompose complex questions into simple sub-questions compared to pre-thinking mechanism. Therefore, a plug-and-play adaptive-thinking mechanism is proposed with the aid of the soft prompt tuning to integrate the merits of the pre-thinking mechanism and post-thinking mechanism, in which a perception module is introduced to adaptively prompt SLM answer or think first based on perceiving the complexity of the questions. Extensive experiments are conducted across 12 reasoning tasks and 2 representative language models to demonstrate the effectiveness of the proposed mechanism.

Related papers

• Recursive Introspection: Teaching Language Model Agents How to Self-Improve [30.086494067593268]
  We develop RISE: Recursive IntroSpEction, an approach for fine-tuning large language models. Our experiments show that RISE enables Llama2, Llama3, and Mistral models to improve themselves with more turns on math reasoning tasks.
  arXiv  Detail & Related papers  (2024-07-25T17:35:59Z)
• Crafting Interpretable Embeddings by Asking LLMs Questions [89.49960984640363]
  Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks. We introduce question-answering embeddings (QA-Emb), embeddings where each feature represents an answer to a yes/no question asked to an LLM. We use QA-Emb to flexibly generate interpretable models for predicting fMRI voxel responses to language stimuli.
  arXiv  Detail & Related papers  (2024-05-26T22:30:29Z)
• Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models [84.15513004135576]
  Current research enhances the reasoning performance of Large Language Models (LLMs) by sampling multiple reasoning chains and ensembling based on the answer frequency. This approach fails in scenarios where the correct answers are in the minority. We introduce a hierarchical reasoning aggregation framework AoR, which selects answers based on the evaluation of reasoning chains.
  arXiv  Detail & Related papers  (2024-05-21T17:12:19Z)
• What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models [50.97705264224828]
  We propose Counterfactual Inception, a novel method that implants counterfactual thinking into Large Multi-modal Models. We aim for the models to engage with and generate responses that span a wider contextual scene understanding. Comprehensive analyses across various LMMs, including both open-source and proprietary models, corroborate that counterfactual thinking significantly reduces hallucination.
  arXiv  Detail & Related papers  (2024-03-20T11:27:20Z)
• Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach [55.613461060997004]
  Large Language Models (LLMs) have catalyzed transformative advances across a spectrum of natural language processing tasks. We propose an innovative textitmetacognitive approach, dubbed textbfCLEAR, to equip LLMs with capabilities for self-aware error identification and correction.
  arXiv  Detail & Related papers  (2024-03-08T19:18:53Z)
• On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks [19.476470154121188]
  We present a principled empirical study of the performance of GPT-4 in three domains: Game of 24, Graph Coloring, and STRIPS planning. We observe significant performance collapse with self-critique, significant performance gains with sound external verification, but that the content of critique doesn't matter to the performance of the system.
  arXiv  Detail & Related papers  (2024-02-12T23:11:01Z)
• Latent Skill Discovery for Chain-of-Thought Reasoning [44.30408985857306]
  We introduce Reasoning Skill Discovery (RSD) that use unsupervised learning to create a latent space representation of rationales. This can then guide the selection of examples that demonstrate the required reasoning skills. Empirically, RSD outperforms existing methods by up to 6% in terms of the answer accuracy across multiple reasoning tasks.
  arXiv  Detail & Related papers  (2023-12-07T20:36:10Z)
• Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs [58.620269228776294]
  We propose a task-agnostic framework for resolving ambiguity by asking users clarifying questions. We evaluate systems across three NLP applications: question answering, machine translation and natural language inference. We find that intent-sim is robust, demonstrating improvements across a wide range of NLP tasks and LMs.
  arXiv  Detail & Related papers  (2023-11-16T00:18:50Z)
• Concise and Organized Perception Facilitates Reasoning in Large Language Models [32.71672086718057]
  We show that large language models (LLMs) exhibit failure patterns akin to human-like cognitive biases when dealing with disordered and irrelevant content in reasoning tasks. We propose a novel reasoning approach named Concise and Organized Perception (COP) COP carefully analyzes the given statements to identify the most pertinent information while eliminating redundancy efficiently.
  arXiv  Detail & Related papers  (2023-10-05T04:47:49Z)
• ZARA: Improving Few-Shot Self-Rationalization for Small Language Models [29.755148112827502]
  We present a novel approach, Zero-shot Augmentation of Rationale-Answer pairs (ZARA), to automatically construct pseudo-parallel data for self-training. ZARA achieves SOTA performance on the FEB benchmark, for both the task accuracy and the explanation metric.
  arXiv  Detail & Related papers  (2023-05-12T10:07:12Z)

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.