Related papers: Open-ended Commonsense Reasoning with Unrestricted…
In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, there is no comparably principled basis to justify trust in the content of the text…
Recent advances in Large Language Models (LLMs) have highlighted the challenge of handling long-context tasks, where models need to reason over extensive input contexts to aggregate target information. While Chain-of-Thought (CoT) prompting…
Visual understanding goes well beyond object recognition. With one glance at an image, we can effortlessly imagine the world beyond the pixels: for instance, we can infer people's actions, goals, and mental states. While this task is easy…
An important open question in the use of large language models for knowledge-intensive tasks is how to effectively integrate knowledge from three sources: the model's parametric memory, external structured knowledge, and external…
Despite the success of generative pre-trained language models on a series of text generation tasks, they still suffer in cases where reasoning over underlying commonsense knowledge is required during generation. Existing approaches that…
Language models (LMs) trained on large amounts of data have shown impressive performance on many NLP tasks under the zero-shot and few-shot setup. Here we aim to better understand the extent to which such models learn commonsense knowledge…
In this paper, we investigate deliberation procedures that invite citizens with contextual opinions to explore alternative thinking frames. Contextuality is captured in a simple quantum cognitive model. We show how disagreeing citizens…
Successful completion of reasoning task requires the agent to have relevant prior knowledge or some given context of the world dynamics. Usually, the information provided to the system for a reasoning task is just the query or some…
Visual Commonsense Reasoning (VCR) predicts an answer with corresponding rationale, given a question-image input. VCR is a recently introduced visual scene understanding task with a wide range of applications, including visual question…
Existing benchmarks for frontier models often test specialized, "PhD-level" knowledge that is difficult for non-experts to grasp. In contrast, we present a benchmark with 613 problems based on the NPR Sunday Puzzle Challenge that requires…
Large Language Models (LLMs) leverage step-by-step reasoning to solve complex problems. Standard evaluation practice involves generating a complete reasoning trace and assessing the correctness of the final answer presented at its…
Commonsense reasoning, aiming at endowing machines with a human-like ability to make situational presumptions, is extremely challenging to generalize. For someone who barely knows about "meditation," while is knowledgeable about "singing,"…
Conversational interfaces that allow for intuitive and comprehensive access to digitally stored information remain an ambitious goal. In this thesis, we lay foundations for designing conversational search systems by analyzing the…
Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive…
Recent years have witnessed an increasing interest in training machines with reasoning ability, which deeply relies on accurately and clearly presented clue forms. The clues are usually modeled as entity-aware knowledge in existing studies.…
Classical planning asks for a sequence of operators reaching a given goal. While the most common case is to compute a plan, many scenarios require more than that. However, quantitative reasoning on the plan space remains mostly unexplored.…
Discovering pattern sets or global patterns is an attractive issue from the pattern mining community in order to provide useful information. By combining local patterns satisfying a joint meaning, this approach produces patterns of higher…
A lot of recent machine learning research papers have ``open-ended learning'' in their title. But very few of them attempt to define what they mean when using the term. Even worse, when looking more closely there seems to be no consensus on…
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…
Exploiting relationships among objects has achieved remarkable progress in interpreting images or videos by natural language. Most existing methods resort to first detecting objects and their relationships, and then generating textual…