Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning

• URL: http://arxiv.org/abs/2210.11708v1
• Date: Fri, 21 Oct 2022 03:34:24 GMT
• Title: Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning
• Authors: Xingwei He, Yeyun Gong, A-Long Jin, Weizhen Qi, Hang Zhang, Jian Jiao, Bartuer Zhou, Biao Cheng, SM Yiu and Nan Duan
• Abstract summary: We propose a metric distillation rule to distill knowledge from the metric to the ranker. We further transfer the critical knowledge summarized by the distilled ranker to the retriever. Experimental results on the CommonGen benchmark verify the effectiveness of our proposed method.
• Score: 48.18060169551869
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Commonsense generation aims to generate a realistic sentence describing a daily scene under the given concepts, which is very challenging, since it requires models to have relational reasoning and compositional generalization capabilities. Previous work focuses on retrieving prototype sentences for the provided concepts to assist generation. They first use a sparse retriever to retrieve candidate sentences, then re-rank the candidates with a ranker. However, the candidates returned by their ranker may not be the most relevant sentences, since the ranker treats all candidates equally without considering their relevance to the reference sentences of the given concepts. Another problem is that re-ranking is very expensive, but only using retrievers will seriously degrade the performance of their generation models. To solve these problems, we propose the metric distillation rule to distill knowledge from the metric (e.g., BLEU) to the ranker. We further transfer the critical knowledge summarized by the distilled ranker to the retriever. In this way, the relevance scores of candidate sentences predicted by the ranker and retriever will be more consistent with their quality measured by the metric. Experimental results on the CommonGen benchmark verify the effectiveness of our proposed method: (1) Our generation model with the distilled ranker achieves a new state-of-the-art result. (2) Our generation model with the distilled retriever even surpasses the previous SOTA.

Related papers

• FIRST: Faster Improved Listwise Reranking with Single Token Decoding [56.727761901751194]
  First, we introduce FIRST, a novel listwise LLM reranking approach leveraging the output logits of the first generated identifier to directly obtain a ranked ordering of the candidates. Empirical results demonstrate that FIRST accelerates inference by 50% while maintaining a robust ranking performance with gains across the BEIR benchmark. Our results show that LLM rerankers can provide a stronger distillation signal compared to cross-encoders, yielding substantial improvements in retriever recall after relevance feedback.
  arXiv  Detail & Related papers  (2024-06-21T21:27:50Z)
• ReFIT: Relevance Feedback from a Reranker during Inference [109.33278799999582]
  Retrieve-and-rerank is a prevalent framework in neural information retrieval. We propose to leverage the reranker to improve recall by making it provide relevance feedback to the retriever at inference time.
  arXiv  Detail & Related papers  (2023-05-19T15:30:33Z)
• LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval [68.85686621130111]
  We propose to make a dense retriever align a well-performing lexicon-aware representation model. We evaluate our model on three public benchmarks, which shows that with a comparable lexicon-aware retriever as the teacher, our proposed dense model can bring consistent and significant improvements.
  arXiv  Detail & Related papers  (2022-08-29T15:09:28Z)
• Towards Robust Ranker for Text Retrieval [83.15191578888188]
  A ranker plays an indispensable role in the de facto'retrieval & rerank' pipeline. A ranker plays an indispensable role in the de facto'retrieval & rerank' pipeline.
  arXiv  Detail & Related papers  (2022-06-16T10:27:46Z)
• Adversarial Retriever-Ranker for dense text retrieval [51.87158529880056]
  We present Adversarial Retriever-Ranker (AR2), which consists of a dual-encoder retriever plus a cross-encoder ranker. AR2 consistently and significantly outperforms existing dense retriever methods. This includes the improvements on Natural Questions R@5 to 77.9%(+2.1%), TriviaQA R@5 to 78.2%(+1.4), and MS-MARCO MRR@10 to 39.5%(+1.3%)
  arXiv  Detail & Related papers  (2021-10-07T16:41:15Z)
• Retrieval Enhanced Model for Commonsense Generation [27.808363395849536]
  We propose a novel framework using retrieval methods to enhance both the pre-training and fine-tuning for commonsense generation. We retrieve prototype sentence candidates by concept matching and use them as auxiliary input. We demonstrate experimentally on the large-scale CommonGen benchmark that our approach achieves new state-of-the-art results.
  arXiv  Detail & Related papers  (2021-05-24T09:49:17Z)

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.