Related papers: Rainier: Reinforced Knowledge Introspector for Com…
Commonsense generation is a challenging task of generating a plausible sentence describing an everyday scenario using provided concepts. Its requirement of reasoning over commonsense knowledge and compositional generalization ability even…
Large language models such as Open AI's Generative Pre-trained Transformer (GPT) models are proficient at answering questions, but their knowledge is confined to the information present in their training data. This limitation renders them…
A fundamental ability of humans is to utilize commonsense knowledge in language understanding and question answering. In recent years, many knowledge-enhanced Commonsense Question Answering (CQA) approaches have been proposed. However, it…
Retrieval-Augmented-Generation and Generation-Augmented-Generation have been proposed to enhance the knowledge required for question answering with Large Language Models (LLMs) by leveraging richer context. However, the former relies on…
Commonsense inference to understand and explain human language is a fundamental research problem in natural language processing. Explaining human conversations poses a great challenge as it requires contextual understanding, planning,…
Machine reading comprehension (MRC) requires reasoning about both the knowledge involved in a document and knowledge about the world. However, existing datasets are typically dominated by questions that can be well solved by context…
Knowledge graph (KG) based reasoning has been regarded as an effective means for the analysis of semantic networks and is of great usefulness in areas of information retrieval, recommendation, decision-making, and man-machine interaction.…
Retrieval-Augmented Generation (RAG) has emerged as a prominent method for incorporating domain knowledge into Large Language Models (LLMs). While RAG enhances response relevance by incorporating retrieved domain knowledge in the context,…
Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that get correct answers by chance. We observe that better…
Commonsense generation aims at generating plausible everyday scenario description based on a set of provided concepts. Digging the relationship of concepts from scratch is non-trivial, therefore, we retrieve prototypes from external…
Recently, the community has achieved substantial progress on many commonsense reasoning benchmarks. However, it is still unclear what is learned from the training process: the knowledge, inference capability, or both? We argue that due to…
Recent advances in large-scale pre-training such as GPT-3 allow seemingly high quality text to be generated from a given prompt. However, such generation systems often suffer from problems of hallucinated facts, and are not inherently…
Knowledge facts are typically represented by relational triples, while we observe that some commonsense facts are represented by the triples whose forms are inconsistent with the expression of language. This inconsistency puts forward a…
Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating external evidence, but it also introduces knowledge conflicts when retrieved contextual knowledge (CK) and parametric knowledge (PK) disagree or are…
A retriever, which retrieves relevant knowledge pieces from a knowledge base given a context, is an important component in many natural language processing (NLP) tasks. Retrievers have been introduced in knowledge-grounded dialog systems to…
Reranking documents based on their relevance to a given query is a critical task in information retrieval. Traditional reranking methods often lack transparency and rely on proprietary models, hindering reproducibility and interpretability.…
Knowledge tracing (KT) plays a crucial role in computer-aided education and intelligent tutoring systems, aiming to assess students' knowledge proficiency by predicting their future performance on new questions based on their past response…
Answering questions using pre-trained language models (LMs) and knowledge graphs (KGs) presents challenges in identifying relevant knowledge and performing joint reasoning.We compared LMs (fine-tuned for the task) with the previously…
Relation extraction is an important but challenging task that aims to extract all hidden relational facts from the text. With the development of deep language models, relation extraction methods have achieved good performance on various…
While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling…