Towards Reliable and Fluent Large Language Models: Incorporating Feedback Learning Loops in QA Systems

Large language models (LLMs) have emerged as versatile tools in various daily applications. However, they are fraught with issues that undermine their utility and trustworthiness. These include the incorporation of erroneous references (citation), the generation of hallucinated information (correctness), and the inclusion of superfluous or omission of crucial details (fluency). To ameliorate these concerns, this study makes several key contributions. First, we build a dataset to train a critic model capable of evaluating the citation, correctness, and fluency of responses generated by LLMs in QA systems. Second, we propose an automated feedback mechanism that leverages the critic model to offer real-time feedback on heterogeneous aspects of generated text. Third, we introduce a feedback learning loop that uses this critic model to iteratively improve the performance of the LLM responsible for response generation. Experimental results demonstrate the efficacy of our approach, showing substantial improvements in citation and fluency metrics for ChatGPT, including a 4% precision increase in citation and an approximately 8% enhancement in the MAUVE metric for fluency, while maintaining high levels of correctness.

You Truly Understand What I Need: Intellectual and Friendly Dialogue Agents grounding Knowledge and Persona

To build a conversational agent that interacts fluently with humans, previous studies blend knowledge or personal profile into the pre-trained language model. However, the model that considers knowledge and persona at the same time is still limited, leading to hallucination and a passive way of using personas. We propose an effective dialogue agent that grounds external knowledge and persona simultaneously. The agent selects the proper knowledge and persona to use for generating the answers with our candidate scoring implemented with a poly-encoder. Then, our model generates the utterance with lesser hallucination and more engagingness utilizing retrieval augmented generation with knowledge-persona enhanced query. We conduct experiments on the persona-knowledge chat and achieve state-of-the-art performance in grounding and generation tasks on the automatic metrics. Moreover, we validate the answers from the models regarding hallucination and engagingness through human evaluation and qualitative results. We show our retriever's effectiveness in extracting relevant documents compared to the other previous retrievers, along with the comparison of multiple candidate scoring methods. Code is available at https://github.com/dlawjddn803/INFO

Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis

Existing works for aspect-based sentiment analysis (ABSA) have adopted a unified approach, which allows the interactive relations among subtasks. However, we observe that these methods tend to predict polarities based on the literal meaning of aspect and opinion terms and mainly consider relations implicitly among subtasks at the word level. In addition, identifying multiple aspect-opinion pairs with their polarities is much more challenging. Therefore, a comprehensive understanding of contextual information w.r.t. the aspect and opinion are further required in ABSA. In this paper, we propose Deep Contextualized Relation-Aware Network (DCRAN), which allows interactive relations among subtasks with deep contextual information based on two modules (i.e., Aspect and Opinion Propagation and Explicit Self-Supervised Strategies). Especially, we design novel self-supervised strategies for ABSA, which have strengths in dealing with multiple aspects. Experimental results show that DCRAN significantly outperforms previous state-of-the-art methods by large margins on three widely used benchmarks.

Auxiliary Sequence Labeling Tasks for Disfluency Detection

Detecting disfluencies in spontaneous speech is an important preprocessing step in natural language processing and speech recognition applications. In this paper, we propose a method utilizing named entity recognition (NER) and part-of-speech (POS) as auxiliary sequence labeling (SL) tasks for disfluency detection. First, we show that training a disfluency detection model with auxiliary SL tasks can improve its F-score in disfluency detection. Then, we analyze which auxiliary SL tasks are influential depending on baseline models. Experimental results on the widely used English Switchboard dataset show that our method outperforms the previous state-of-the-art in disfluency detection.

Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection

In this paper, we study the task of selecting optimal response given user and system utterance history in retrieval-based multi-turn dialog systems. Recently, pre-trained language models (e.g., BERT, RoBERTa, and ELECTRA) have shown significant improvements in various natural language processing tasks. This and similar response selection tasks can also be solved using such language models by formulating them as dialog-response binary classification tasks. Although existing works using this approach successfully obtained state-of-the-art results, we observe that language models trained in this manner tend to make predictions based on the relatedness of history and candidates, ignoring the sequential nature of multi-turn dialog systems. This suggests that the response selection task alone is insufficient in learning temporal dependencies between utterances. To this end, we propose utterance manipulation strategies (UMS) to address this problem. Specifically, UMS consist of several strategies (i.e., insertion, deletion, and search), which aid the response selection model towards maintaining dialog coherence. Further, UMS are self-supervised methods that do not require additional annotation and thus can be easily incorporated into existing approaches. Extensive evaluation across multiple languages and models shows that UMS are highly effective in teaching dialog consistency, which lead to models pushing the state-of-the-art with significant margins on multiple public benchmark datasets.

Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization

Text summarization refers to the process that generates a shorter form of text from the source document preserving salient information. Recently, many models for text summarization have been proposed. Most of those models were evaluated using recall-oriented understudy for gisting evaluation (ROUGE) scores. However, as ROUGE scores are computed based on n-gram overlap, they do not reflect semantic meaning correspondences between generated and reference summaries. Because Korean is an agglutinative language that combines various morphemes into a word that express several meanings, ROUGE is not suitable for Korean summarization. In this paper, we propose evaluation metrics that reflect semantic meanings of a reference summary and the original document, Reference and Document Aware Semantic Score (RDASS). We then propose a method for improving the correlation of the metrics with human judgment. Evaluation results show that the correlation with human judgment is significantly higher for our evaluation metrics than for ROUGE scores.

Domain Adaptive Training BERT for Response Selection

We focus on multi-turn response selection in a retrieval-based dialog system. In this paper, we utilize the powerful pre-trained language model Bi-directional Encoder Representations from Transformer (BERT) for a multi-turn dialog system and propose a highly effective post-training method on domain-specific corpus. Although BERT is easily adopted to various NLP tasks and outperforms previous baselines of each task, it still has limitations if a task corpus is too focused on a certain domain. Post-training on domain-specific corpus (e.g., Ubuntu Corpus) helps the model to train contextualized representations and words that do not appear in general corpus (e.g.,English Wikipedia). Experiment results show that our approach achieves new state-of-the-art on two response selection benchmark datasets (i.e.,Ubuntu Corpus V1, Advising Corpus) performance improvement by 5.9% and 6% on Recall@1.

EmotionX-KU: BERT-Max based Contextual Emotion Classifier

We propose a contextual emotion classifier based on a transferable language model and dynamic max pooling, which predicts the emotion of each utterance in a dialogue. A representative emotion analysis task, EmotionX, requires to consider contextual information from colloquial dialogues and to deal with a class imbalance problem. To alleviate these problems, our model leverages the self-attention based transferable language model and the weighted cross entropy loss. Furthermore, we apply post-training and fine-tuning mechanisms to enhance the domain adaptability of our model and utilize several machine learning techniques to improve its performance. We conduct experiments on two emotion-labeled datasets named Friends and EmotionPush. As a result, our model outperforms the previous state-of-the-art model and also shows competitive performance in the EmotionX 2019 challenge. The code will be available in the Github page.

Character-Level Feature Extraction with Densely Connected Networks

Generating character-level features is an important step for achieving good results in various natural language processing tasks. To alleviate the need for human labor in generating hand-crafted features, methods that utilize neural architectures such as Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) to automatically extract such features have been proposed and have shown great results. However, CNN generates position-independent features, and RNN is slow since it needs to process the characters sequentially. In this paper, we propose a novel method of using a densely connected network to automatically extract character-level features. The proposed method does not require any language or task specific assumptions, and shows robustness and effectiveness while being faster than CNN- or RNN-based methods. Evaluating this method on three sequence labeling tasks - slot tagging, Part-of-Speech (POS) tagging, and Named-Entity Recognition (NER) - we obtain state-of-the-art performance with a 96.62 F1-score and 97.73% accuracy on slot tagging and POS tagging, respectively, and comparable performance to the state-of-the-art 91.13 F1-score on NER.