Related papers: PreWoMe: Exploiting Presuppositions as Working Mem…
Large language models (LLMs) often respond confidently to questions even when they lack the necessary information, leading to hallucinated answers. In this work, we study the problem of (un)answerability detection, focusing on extractive…
Despite their impressive performance on diverse tasks, large language models (LMs) still struggle with tasks requiring rich world knowledge, implying the limitations of relying solely on their parameters to encode a wealth of world…
The rise of large language models (LLMs) has revolutionized the way that we interact with artificial intelligence systems through natural language. However, LLMs often misinterpret user queries because of their uncertain intention, leading…
Self-Consistency samples diverse reasoning chains with answers and chooses the final answer by majority voting. It is based on forward reasoning and cannot further improve performance by sampling more reasoning chains when saturated. To…
Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation, which inflate computational costs and even degrade performance. Inspired by human…
Retrieval-based code question answering seeks to match user queries in natural language to relevant code snippets. Previous approaches typically rely on pretraining models using crafted bi-modal and uni-modal datasets to align text and code…
Large language models (LLMs) have demonstrated remarkable capabilities in language generation, understanding, and few-shot learning in recent years. An extensive body of work has explored how their performance may be further improved…
Teaching Visual Question Answering (VQA) models to refrain from answering unanswerable questions is necessary for building a trustworthy AI system. Existing studies, though have explored various aspects of VQA but somewhat ignored this…
Hallucination remains a major challenge for the safe and trustworthy deployment of large language models (LLMs) in factual content generation. Prior work has explored confidence estimation as an effective approach to hallucination…
As we embark on a new era of LLMs, it becomes increasingly crucial to understand their capabilities, limitations, and differences. Toward making further progress in this direction, we strive to build a deeper understanding of the gaps…
Recent work suggests that large language models enhanced with retrieval-augmented generation are easily influenced by the order, in which the retrieved documents are presented to the model when solving tasks such as question answering (QA).…
Language models retain a significant amount of world knowledge from their pre-training stage. This allows knowledgeable models to be applied to knowledge-intensive tasks prevalent in information retrieval, such as ranking or question…
Pre-trained Generative models such as BART, T5, etc. have gained prominence as a preferred method for text generation in various natural language processing tasks, including abstractive long-form question answering (QA) and summarization.…
Working memory (WM), a fundamental cognitive process facilitating the temporary storage, integration, manipulation, and retrieval of information, plays a vital role in reasoning and decision-making tasks. Robust benchmark datasets that…
Automatic fact-checking plays a crucial role in combating the spread of misinformation. Large Language Models (LLMs) and Instruction-Following variants, such as InstructGPT and Alpaca, have shown remarkable performance in various natural…
Answering complex questions that require making latent decisions is a challenging task, especially when limited supervision is available. Recent works leverage the capabilities of large language models (LMs) to perform complex question…
Probing is a popular method to discern what linguistic information is contained in the representations of pre-trained language models. However, the mechanism of selecting the probe model has recently been subject to intense debate, as it is…
Emotion cause extraction aims to identify the reasons behind a certain emotion expressed in text. It is a much more difficult task compared to emotion classification. Inspired by recent advances in using deep memory networks for question…
When language models are trained on textual data, they acquire both knowledge about the structure of language as well as knowledge of facts about the world. At inference time, their knowledge of facts can be leveraged to solve interesting…
Knowledge base question answering (KBQA) is a critical yet challenging task due to the vast number of entities within knowledge bases and the diversity of natural language questions posed by users. Unfortunately, the performance of most…