QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models

• URL: http://arxiv.org/abs/2405.13014v1
• Date: Tue, 14 May 2024 13:07:10 GMT
• Title: QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models
• Authors: Wei Wang, Zhaowei Li, Qi Xu, Yiqing Cai, Hang Song, Qi Qi, Ran Zhou, Zhida Huang, Tao Wang, Li Xiao,
• Abstract summary: We propose a general approach called quality-guided contrastive rationale distillation for reasoning capacity learning. For the learning of positive knowledge, we collect rationales through self-consistency to denoise the LLM rationales generated by temperature sampling. For the negative knowledge distillation, we generate negative rationales using temperature sampling for the iteration-before smaller language models themselves.
• Score: 13.54030164748731
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deploying large language models (LLMs) poses challenges in terms of resource limitations and inference efficiency. To address these challenges, recent research has focused on using smaller task-specific language models, which are enhanced by distilling the knowledge rationales generated by LLMs. However, previous works mostly emphasize the effectiveness of positive knowledge, while overlooking the knowledge noise and the exploration of negative knowledge. In this paper, we first propose a general approach called quality-guided contrastive rationale distillation for reasoning capacity learning, considering contrastive learning perspectives. For the learning of positive knowledge, we collect positive rationales through self-consistency to denoise the LLM rationales generated by temperature sampling. For the negative knowledge distillation, we generate negative rationales using temperature sampling for the iteration-before smaller language models themselves. Finally, a contrastive loss is designed to better distill the positive and negative rationales into the smaller language model, where an online-update discriminator is used to judge the qualities of rationales and assign weights for better optimizing the training process. Through extensive experiments on multiple reasoning tasks, we demonstrate that our method consistently outperforms the previous distillation methods and produces higher-quality rationales.

Related papers

• LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning [21.12539851761666]
  Large language models (LLMs) sometimes demonstrate poor performance on knowledge-intensive tasks. We propose a novel method named eliciting, filtering and integrating knowledge in large language model (LINKED) With our comprehensive experiments on two complex commonsense reasoning benchmarks, our method outperforms SOTA baselines (up to 9.0% improvement of accuracy)
  arXiv  Detail & Related papers  (2024-10-12T14:12:22Z)
• Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review [11.756344944226495]
  We introduce a novel Fault-Aware DistIllation via Peer-Review (FAIR) approach. Instead of merely obtaining rationales from teachers, our method asks teachers to identify and explain the student's mistakes.
  arXiv  Detail & Related papers  (2024-10-04T17:59:41Z)
• FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation [29.606646251624923]
  Fine-tuning is still far away from satisfactory trustworthiness due to "tuning-induced mis-calibration" We propose Efficient Trustworthy Distillation (FIRST), which utilizes a small portion of teacher's knowledge to obtain a reliable language model in a cost-efficient way. Experimental results demonstrate the effectiveness of our method, where better accuracy (+2.3%) and less miscalibration (-10%) are achieved.
  arXiv  Detail & Related papers  (2024-08-22T07:31:00Z)
• Multi-Granularity Semantic Revision for Large Language Model Distillation [66.03746866578274]
  We propose a multi-granularity semantic revision method for LLM distillation. At the sequence level, we propose a sequence correction and re-generation strategy. At the token level, we design a distribution adaptive clipping Kullback-Leibler loss as the distillation objective function. At the span level, we leverage the span priors of a sequence to compute the probability correlations within spans, and constrain the teacher and student's probability correlations to be consistent.
  arXiv  Detail & Related papers  (2024-07-14T03:51:49Z)
• Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
  We study how well large language models (LLMs) explain their generations through rationales. We show that prompting-based methods are less "faithful" than attribution-based explanations.
  arXiv  Detail & Related papers  (2024-06-28T20:06:30Z)
• Unlearning with Control: Assessing Real-world Utility for Large Language Model Unlearning [97.2995389188179]
  Recent research has begun to approach large language models (LLMs) unlearning via gradient ascent (GA) Despite their simplicity and efficiency, we suggest that GA-based methods face the propensity towards excessive unlearning. We propose several controlling methods that can regulate the extent of excessive unlearning.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• ELAD: Explanation-Guided Large Language Models Active Distillation [16.243249111524403]
  The deployment and application of Large Language Models (LLMs) is hindered by their memory inefficiency, computational demands, and the high costs of API inferences. Traditional distillation methods, which transfer the capabilities of LLMs to smaller models, often fail to determine whether the knowledge has been sufficiently transferred. We propose an Explanation-Guided LLMs Active Distillation (ELAD) framework that employs an active learning strategy to optimize the balance between annotation costs and model performance.
  arXiv  Detail & Related papers  (2024-02-20T15:47:59Z)
• SCOTT: Self-Consistent Chain-of-Thought Distillation [68.40232422158569]
  Large language models (LMs) generate free-text rationales for their predictions via chain-of-thought prompting. We propose a faithful knowledge distillation method to learn a small, self-consistent CoT model from a teacher model that is orders of magnitude larger. To ensure faithful distillation, we use the teacher-generated rationales to learn a student LM with a counterfactual reasoning objective.
  arXiv  Detail & Related papers  (2023-05-03T03:47:00Z)
• NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models [54.184609286094044]
  We propose noise entropy regularisation (NoiER) as an efficient learning paradigm that solves the problem without auxiliary models and additional data. The proposed approach improved traditional OOD detection evaluation metrics by 55% on average compared to the original fine-tuned models.
  arXiv  Detail & Related papers  (2021-08-29T06:58:28Z)
• Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems [84.3996727203154]
  We show that a popular choice of contrastive loss is equivalent to reducing the exposure bias via inverse propensity weighting. We further improve upon CLRec and propose Multi-CLRec, for accurate multi-intention aware bias reduction. Our methods have been successfully deployed in Taobao, where at least four-month online A/B tests and offline analyses demonstrate its substantial improvements.
  arXiv  Detail & Related papers  (2020-05-20T08:15:23Z)

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.