Although Retrieval-Augmented Large Language Models (RALMs) demonstrate their superiority in terms of factuality, they do not consistently outperform the original retrieval-free Language Models (LMs). Our experiments reveal that this example-level performance inconsistency exists not only between retrieval-augmented and retrieval-free LM but also among different retrievers. To understand this phenomenon, we investigate the degeneration behavior of RALMs and theoretically decompose it into four categories. Further analysis based on our decomposition reveals that the innate difference in knowledge sources and the unpredictable degeneration of the reader model contribute most to the inconsistency. Drawing from our analysis, we introduce Ensemble of Retrievers (EoR), a trainable framework that can adaptively retrieve from different knowledge sources and effectively decrease unpredictable reader errors. Our experiments on Open Domain Question Answering show that EoR substantially improves performance over the RALM with a single retriever by considerably reducing inconsistent behaviors.

This paper introduces a novel Self-supervised Fine-grained Dialogue Evaluation framework (SelF-Eval). The core idea is to model the correlation between turn quality and the entire dialogue quality. We first propose a novel automatic data construction method that can automatically assign fine-grained scores for arbitrarily dialogue data. Then we train SelF-Eval with a multi-level contrastive learning schema which helps to distinguish different score levels. Experimental results on multiple benchmarks show that SelF-Eval is highly consistent with human evaluations and better than the state-of-the-art models. We give a detailed analysis of the experiments in this paper. Our code is available on GitHub.

We participate in the DialDoc Shared Task sub-task 1 (Knowledge Identification). The task requires identifying the grounding knowledge in form of a document span for the next dialogue turn. We employ two well-known pre-trained language models (RoBERTa and ELECTRA) to identify candidate document spans and propose a metric-based ensemble method for span selection. Our methods include data augmentation, model pre-training/fine-tuning, post-processing, and ensemble. On the submission page, we rank 2nd based on the average of normalized F1 and EM scores used for the final evaluation. Specifically, we rank 2nd on EM and 3rd on F1.

Currently, in spoken language understanding (SLU) systems, the automatic speech recognition (ASR) module produces multiple interpretations (or hypotheses) for the input audio signal and the natural language understanding (NLU) module takes the one with the highest confidence score for domain or intent classification. However, the interpretations can be noisy, and solely relying on one interpretation can cause information loss. To address the problem, many research works attempt to rerank the interpretations for a better choice while some recent works get better performance by integrating all the hypotheses during prediction. In this paper, we follow the way of integrating hypotheses but strengthen the training mode by involving more tasks, some of which may be not in existing tasks of NLU but relevant, via multi-task learning or transfer learning. Moreover, we propose the Hierarchical Attention Mechanism (HAM) to further improve the performance with the acoustic-model features like confidence scores, which are ignored in the current hypotheses integration models. The experimental results show that compared to the standard estimation with one hypothesis, the multi-task learning with HAM can improve the domain and intent classification by relatively 19% and 37%, which are much higher than improvements with current integration or reranking methods. To illustrate the cause of improvements brought by our model, we decode the hidden representations of some utterance examples and compare the generated texts with hypotheses and transcripts. The comparison shows that our model could recover the transcription by integrating the fragmented information among hypotheses and identifying the frequent error patterns of the ASR module, and even rewrite the query for a better understanding, which reveals the characteristic of multi-task learning of broadcasting knowledge.