Related papers: A Factuality and Diversity Reconciled Decoding Met…
Factual correctness is often the limiting factor in practical applications of natural language generation in high-stakes domains such as healthcare. An essential requirement for maintaining factuality is the ability to deal with rare…
Counterfactual generation lies at the core of various machine learning tasks, including image translation and controllable text generation. This generation process usually requires the identification of the disentangled latent…
Knowledge-grounded dialogue systems aim to generate coherent and engaging responses based on the dialogue contexts and selected external knowledge. Previous knowledge selection methods tend to rely too heavily on the dialogue contexts or…
Recent progress in pre-trained language models led to systems that are able to generate text of an increasingly high quality. While several works have investigated the fluency and grammatical correctness of such models, it is still unclear…
Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation. As bland and generic utterances usually dominate the frequency distribution in our…
Large language models can generate factually inaccurate content, a problem known as hallucination. Recent works have built upon retrieved-augmented generation to improve factuality through iterative prompting but these methods are limited…
Pretrained language models (LMs) are susceptible to generate text with nonfactual information. In this work, we measure and improve the factual accuracy of large-scale LMs for open-ended text generation. We design the FactualityPrompts test…
Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…
Large language models (LLMs) are documented to struggle in settings that require complex reasoning. Nevertheless, instructing the model to break down the problem into smaller reasoning steps, or ensembling various generations through…
While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to…
Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses. However, these models are still prone to produce hallucinated responses not supported by the input source, which…
Self-consistency has emerged as a powerful method for improving the accuracy of short answers generated by large language models. As previously defined, it only concerns the accuracy of a final answer parsed from generated text. In this…
Information-seeking dialogues span a wide range of questions, from simple factoid to complex queries that require exploring multiple facets and viewpoints. When performing exploratory searches in unfamiliar domains, users may lack…
End-to-End intelligent neural dialogue systems suffer from the problems of generating inconsistent and repetitive responses. Existing dialogue models pay attention to unilaterally incorporating personal knowledge into the dialog while…
In empathetic conversations, individuals express their empathy towards others. Previous work has mainly focused on generating empathetic responses by utilizing the speaker's emotion. Besides, external commonsense knowledge has been applied…
Incorporating external knowledge into dialogue generation (KIDG) is crucial for improving the correctness of response, where evidence fragments serve as knowledgeable snippets supporting the factual dialogue replies. However, introducing…
Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered…
Obtaining multiple meaningfully diverse, high quality samples from Large Language Models for a fixed prompt remains an open challenge. Current methods for increasing diversity often only operate at the token-level, paraphrasing the same…
Linguistic pragmatics state that a conversation's underlying speech acts can constrain the type of response which is appropriate at each turn in the conversation. When generating dialogue responses, neural dialogue agents struggle to…
Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when solely relying on their internal knowledge, especially when answering questions that require less commonly known…