Related papers: Retrieve and Refine: Improved Sequence Generation …

Language models are often used as the backbone of modern dialogue systems. These models are pre-trained on large amounts of written fluent language. Repetition is typically penalised when evaluating language model generations. However, it…

The wave of pre-training language models has been continuously improving the quality of the machine-generated conversations, however, some of the generated responses still suffer from excessive repetition, sometimes repeating words from…

In the era of large language models, applying techniques such as Retrieval Augmented Generation can better address Open-Domain Question-Answering problems. Due to constraints including model sizes and computing resources, the length of…

Retrieval-augmented language models (RALMs) hold promise to produce language understanding systems that are are factual, efficient, and up-to-date. An important desideratum of RALMs, is that retrieved information helps model performance…

How to effectively utilize the dialogue history is a crucial problem in multi-turn dialogue generation. Previous works usually employ various neural network architectures (e.g., recurrent neural networks, attention mechanisms, and…

Augmenting Large Language Models (LLMs) with information retrieval capabilities (i.e., Retrieval-Augmented Generation (RAG)) has proven beneficial for knowledge-intensive tasks. However, understanding users' contextual search intent when…

Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to capture the rich interactions between dialogue context and…

Knowledge retrieval is one of the major challenges in building a knowledge-grounded dialogue system. A common method is to use a neural retriever with a distributed approximate nearest-neighbor database to quickly find the relevant…

Being able to generate informative and coherent dialogue responses is crucial when designing human-like open-domain dialogue systems. Encoder-decoder-based dialogue models tend to produce generic and dull responses during the decoding step…

Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems. Though highly efficient in learning the backbone of human-computer communications, they suffer from the problem of…

The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context. Until now, the existing models for this task suffer from the robustness issue, i.e., performances…

Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them. This has resulted in the development of models which treat conversation as a sequence-to-sequence…

Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address. They tend to produce generations that (i) rely too much on copying from the context, (ii) contain repetitions…

Retrieval-augmented generation resorts to content retrieved from external sources in order to leverage the performance of large language models in downstream tasks. The excessive volume of retrieved content, the possible dispersion of its…

While language models (LMs) have proven remarkably adept at generating code, many programs are challenging for LMs to generate using their parametric knowledge alone. Providing external contexts such as library documentation can facilitate…

Generative models for open domain question answering have proven to be competitive, without resorting to external knowledge. While promising, this approach requires to use models with billions of parameters, which are expensive to train and…

Relation triple extraction, which outputs a set of triples from long sentences, plays a vital role in knowledge acquisition. Large language models can accurately extract triples from simple sentences through few-shot learning or fine-tuning…

Although pre-trained sequence-to-sequence models have achieved great success in dialogue response generation, chatbots still suffer from generating inconsistent responses in real-world practice, especially in multi-turn settings. We argue…

In comparison to the interpretation of classification models, the explanation of sequence generation models is also an important problem, however it has seen little attention. In this work, we study model-agnostic explanations of a…

In retrieval-augmented generation (RAG) question answering systems, generating citations for large language model (LLM) outputs enhances verifiability and helps users identify potential hallucinations. However, we observe two problems in…