PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems

• URL: http://arxiv.org/abs/2309.10413v1
• Date: Tue, 19 Sep 2023 08:27:09 GMT
• Title: PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems
• Authors: Bryan Wilie, Yan Xu, Willy Chung, Samuel Cahyawijaya, Holy Lovenia, Pascale Fung
• Abstract summary: Current knowledge-grounded dialogue systems often fail to align the generated responses with human-preferred qualities. We propose Polished & Informed Candidate Scoring (PICK), a generation re-scoring framework. We demonstrate the effectiveness of PICK in generating responses that are more faithful while keeping them relevant to the dialogue history.
• Score: 59.1250765143521
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Grounding dialogue response generation on external knowledge is proposed to produce informative and engaging responses. However, current knowledge-grounded dialogue (KGD) systems often fail to align the generated responses with human-preferred qualities due to several issues like hallucination and the lack of coherence. Upon analyzing multiple language model generations, we observe the presence of alternative generated responses within a single decoding process. These alternative responses are more faithful and exhibit a comparable or higher level of relevance to prior conversational turns compared to the optimal responses prioritized by the decoding processes. To address these challenges and driven by these observations, we propose Polished \& Informed Candidate Scoring (PICK), a generation re-scoring framework that empowers models to generate faithful and relevant responses without requiring additional labeled data or model tuning. Through comprehensive automatic and human evaluations, we demonstrate the effectiveness of PICK in generating responses that are more faithful while keeping them relevant to the dialogue history. Furthermore, PICK consistently improves the system's performance with both oracle and retrieved knowledge in all decoding strategies. We provide the detailed implementation in https://github.com/bryanwilie/pick .

Related papers

• UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems [44.893215129952395]
  Large Language Models (LLMs) has shown exceptional capabilities in many natual language understanding and generation tasks. We decompose the use of multiple sources in generating personalized response into three sub-tasks: Knowledge Source Selection, Knowledge Retrieval, and Response Generation. We propose a novel Unified Multi-Source Retrieval-Augmented Generation system (UniMS-RAG)
  arXiv  Detail & Related papers  (2024-01-24T06:50:20Z)
• FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems [53.89014188309486]
  We present a flexible neural framework that can integrate contextual information from multiple channels. We evaluate our model on the MSDialog dataset widely used for evaluating conversational response ranking tasks.
  arXiv  Detail & Related papers  (2023-03-31T23:58:28Z)
• Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production [98.98161995555485]
  We propose a dialogue model that can access the vast and dynamic information from any search engine for response generation. As the core module, a query producer is used to generate queries from a dialogue context to interact with a search engine. Experiments show that our query producer can achieve R@1 and R@5 rates of 62.4% and 74.8% for retrieving gold knowledge.
  arXiv  Detail & Related papers  (2023-02-16T01:58:10Z)
• Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems [71.33737787564966]
  End-to-end (E2E) task-oriented dialogue (ToD) systems are prone to fall into the so-called 'likelihood trap' We propose a reranking method which aims to select high-quality items from the lists of responses initially overgenerated by the system. Our methods improve a state-of-the-art E2E ToD system by 2.4 BLEU, 3.2 ROUGE, and 2.8 METEOR scores, achieving new peak results.
  arXiv  Detail & Related papers  (2022-11-07T15:59:49Z)
• Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injection [37.15893335147598]
  A limitation of current neural dialog models is that they tend to suffer from a lack of specificity and informativeness in generated responses. We propose a post-hoc knowledge-injection technique where we first retrieve a diverse set of relevant knowledge snippets conditioned on both the dialog history and an initial response from an existing dialog model. We construct multiple candidate responses, individually injecting each retrieved snippet into the initial response using a gradient-based decoding method, and then select the final response with an unsupervised ranking step.
  arXiv  Detail & Related papers  (2022-03-22T00:42:27Z)
• WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue [17.663449579168297]
  We simulate a dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other. The agent uses dynamic blocking to generate ranked diverse responses and exploration-exploitation to select among the Top-K responses. Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation.
  arXiv  Detail & Related papers  (2021-08-01T08:00:45Z)
• Improving Response Quality with Backward Reasoning in Open-domain Dialogue Systems [53.160025961101354]
  We propose to train the generation model in a bidirectional manner by adding a backward reasoning step to the vanilla encoder-decoder training. The proposed backward reasoning step pushes the model to produce more informative and coherent content. Our method can improve response quality without introducing side information.
  arXiv  Detail & Related papers  (2021-04-30T20:38:27Z)
• Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues [88.73739515457116]
  We introduce four self-supervised tasks including next session prediction, utterance restoration, incoherence detection and consistency discrimination. We jointly train the PLM-based response selection model with these auxiliary tasks in a multi-task manner. Experiment results indicate that the proposed auxiliary self-supervised tasks bring significant improvement for multi-turn response selection.
  arXiv  Detail & Related papers  (2020-09-14T08:44:46Z)

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.