Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation

• URL: http://arxiv.org/abs/2402.07092v3
• Date: Tue, 4 Jun 2024 02:09:15 GMT
• Title: Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation
• Authors: Haonan Chen, Zhicheng Dou, Kelong Mao, Jiongnan Liu, Ziliang Zhao,
• Abstract summary: Existing conversational dense retrieval models mostly view a conversation as a fixed sequence of questions and responses. We propose a framework for generalizing Conversational dense retrieval via LLM-cognition data Augmentation (ConvAug) Inspired by human cognition, we devise a cognition-aware process to mitigate the generation of false positives, false negatives, and hallucinations.
• Score: 25.578440131793858
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conversational search utilizes muli-turn natural language contexts to retrieve relevant passages. Existing conversational dense retrieval models mostly view a conversation as a fixed sequence of questions and responses, overlooking the severe data sparsity problem -- that is, users can perform a conversation in various ways, and these alternate conversations are unrecorded. Consequently, they often struggle to generalize to diverse conversations in real-world scenarios. In this work, we propose a framework for generalizing Conversational dense retrieval via LLM-cognition data Augmentation (ConvAug). ConvAug first generates multi-level augmented conversations to capture the diverse nature of conversational contexts. Inspired by human cognition, we devise a cognition-aware process to mitigate the generation of false positives, false negatives, and hallucinations. Moreover, we develop a difficulty-adaptive sample filter that selects challenging samples for complex conversations, thereby giving the model a larger learning space. A contrastive learning objective is then employed to train a better conversational context encoder. Extensive experiments conducted on four public datasets, under both normal and zero-shot settings, demonstrate the effectiveness, generalizability, and applicability of ConvAug. The code is released at https://github.com/haon-chen/ConvAug.

Related papers

• Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State Tracking [16.37636420517529]
  Large language models (LLMs) let us unlock the commonsense connections between user preference utterances and complex language in user-generated reviews. RA-Rec is a dialogue state tracking system for ConvRec, showcased with a video, open source GitHub repository, and interactive Google Colab notebook.
  arXiv  Detail & Related papers  (2024-05-25T15:41:26Z)
• Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries [48.243879779374836]
  Few-shot dialogue state tracking (DST) with Large Language Models (LLM) relies on an effective and efficient conversation retriever to find similar in-context examples for prompt learning. Previous works use raw dialogue context as search keys and queries, and a retriever is fine-tuned with annotated dialogues to achieve superior performance. We handle the task of conversation retrieval based on text summaries of the conversations. A LLM-based conversation summarizer is adopted for query and key generation, which enables effective maximum inner product search.
  arXiv  Detail & Related papers  (2024-02-20T14:31:17Z)
• CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generation [32.10366004426449]
  We propose CONVERSER, a framework for training conversational dense retrievers with at most 6 examples of in-domain dialogues. We utilize the in-context learning capability of large language models to generate conversational queries given a passage in the retrieval corpus. Experimental results on conversational retrieval benchmarks OR-QuAC and TREC CAsT 19 show that the proposed CONVERSER achieves comparable performance to fully-supervised models.
  arXiv  Detail & Related papers  (2023-09-13T06:40:24Z)
• History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System [59.78425104243993]
  We propose History-Aware Hierarchical Transformer (HAHT) for multi-session open-domain dialogue. HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context. Experimental results on a large-scale Multi-Session Conversation dataset suggest that the proposed HAHT model consistently outperforms baseline models.
  arXiv  Detail & Related papers  (2023-02-02T06:54:33Z)
• Talk the Walk: Synthetic Data Generation for Conversational Music Recommendation [62.019437228000776]
  We present TalkWalk, which generates realistic high-quality conversational data by leveraging encoded expertise in widely available item collections. We generate over one million diverse conversations in a human-collected dataset.
  arXiv  Detail & Related papers  (2023-01-27T01:54:16Z)
• TikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real World [97.58623810402563]
  We introduce a new video-based multi-modal dialogue dataset, called TikTalk. We collect 38K videos from a popular video-sharing platform, along with 367K conversations posted by users beneath them. Users engage in spontaneous conversations based on their multi-modal experiences from watching videos, which helps recreate real-world chitchat context.
  arXiv  Detail & Related papers  (2023-01-14T10:18:22Z)
• Knowledge-Grounded Conversational Data Augmentation with Generative Conversational Networks [76.11480953550013]
  We take a step towards automatically generating conversational data using Generative Conversational Networks. We evaluate our approach on conversations with and without knowledge on the Topical Chat dataset.
  arXiv  Detail & Related papers  (2022-07-22T22:37:14Z)
• A Neural Conversation Generation Model via Equivalent Shared Memory Investigation [39.922967513749654]
  We propose a novel reading and memory framework called Deep Reading Memory Network (DRMN) DRMN is capable of remembering useful information of similar conversations for improving utterance generation. We apply our model to two large-scale conversation datasets of justice and e-commerce fields.
  arXiv  Detail & Related papers  (2021-08-20T13:20:14Z)
• Summary Grounded Conversation Generation [10.470157142861174]
  We show how pre-trained language models can be used to generate entire conversations, given only a summary of a conversation as the input. We also show that the accuracy of conversation summarization can be improved by augmenting a conversation summarization dataset with generated conversations.
  arXiv  Detail & Related papers  (2021-06-07T04:46:31Z)
• Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension [49.92173751203827]
  In multi-turn dialog, utterances do not always take the full form of sentences. We propose to improve the response generation performance by examining the model's ability to answer a reading comprehension question.
  arXiv  Detail & Related papers  (2020-12-14T10:58:01Z)

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.