Arrow Research search

Author name cluster

Bin Gong

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
2 author rows

Possible papers

2

ECAI Conference 2024 Conference Paper

Iteratively Calibrating Prompts for Unsupervised Diverse Opinion Summarization

  • Jian Wang 0118
  • Yuqing Sun 0001
  • Yanjie Liang
  • Xin Li 0137
  • Bin Gong

Diverse opinion summarization aims to generate a summary that captures multiple opinions in texts. Although large language models (LLMs) have become the main choice for this task, the performance is highly depend on prompts. In this paper, we propose a self-evaluation based prompt calibration framework to stimulate LLM for generating high quality summary. It adopts the reinforcement learning mechanism to calibrate prompts for maximizing the reward of summary. The framework contains three parts. In the prompt construction part, we design the prompt that contains topic, task instruction and key opinion reference. The topic indicates the main focus of documents, the instruction describes the task with natural language and the key opinion reference is the explicit constraint on the expected opinions. In the reward part, for each summary, its coverage score and diversity score are used to represent the semantic coverage to the source documents and the inter opinion differences, respectively. The prompt calibration part selects the sentences in generated summaries to calibrate the prompts for the next iteration. With this framework, we use a LLM with 7B parameters to generate summaries, which outperforms large GPT-4 and multiple strong baselines. The ablation studies indicate the effectiveness of the iterative calibration process. We analyze the opinion difference in terms of the tendencies of sentences in summaries and use the Natural Language Inference (NLI)-based method to evaluate the faithfulness of summaries. Experiment results show that our method generates summaries with high opinion difference and faithfulness.

Details

AAAI Conference 2023 Conference Paper

Unsupervised Paraphrasing under Syntax Knowledge

  • Tianyuan Liu
  • Yuqing Sun
  • Jiaqi Wu
  • Xi Xu
  • Yuchen Han
  • Cheng Li
  • Bin Gong

The soundness of syntax is an important issue for the paraphrase generation task. Most methods control the syntax of paraphrases by embedding the syntax and semantics in the generation process, which cannot guarantee the syntactical correctness of the results. Different from them, in this paper we investigate the structural patterns of word usages termed as the word composable knowledge and integrate it into the paraphrase generation to control the syntax in an explicit way. This syntax knowledge is pretrained on a large corpus with the dependency relationships and formed as the probabilistic functions on the word-level syntactical soundness. For the sentence-level correctness, we design a hierarchical syntax structure loss to quantitatively verify the syntactical soundness of the paraphrase against the given dependency template. Thus, the generation process can select the appropriate words with consideration on both semantics and syntax. The proposed method is evaluated on a few paraphrase datasets. The experimental results show that the quality of paraphrases by our proposed method outperforms the compared methods, especially in terms of syntax correctness.

PDF Details DOI