相关论文: From Parse-Execute to Parse-Execute-Refine: Improv…

Chain-of-Thought (CoT) reasoning is a critical capability for large language models (LLMs), enabling them to tackle com- plex multi-step tasks. While base LLMs, pre-trained on general text corpora, often struggle with reasoning due to a…

While Large Language Models (LLMs) have found success in real-world applications, their underlying explanatory process is still poorly understood. This paper proposes IBE-Eval, a framework inspired by philosophical accounts on Inference to…

Long-context question-answering (LCQA) systems have greatly benefited from the powerful reasoning capabilities of large language models (LLMs), which can be categorized into slow and quick reasoning modes. However, both modes have their…

Many AI applications rely on knowledge encoded in a locigal knowledge base (KB). The most essential benefit of such logical KBs is the opportunity to perform automatic reasoning which however requires a KB to meet some minimal quality…

Integrating large language models (LLMs) with rule-based reasoning offers a powerful solution for improving the flexibility and reliability of Knowledge Base Completion (KBC). Traditional rule-based KBC methods offer verifiable reasoning…

Large Language Models (LLMs) exhibit impressive problem-solving skills across many tasks, but they still underperform compared to humans in various downstream applications, such as text-to-SQL. On the BIRD benchmark leaderboard, human…

Complex question-answering (CQA) involves answering complex natural-language questions on a knowledge base (KB). However, the conventional neural program induction (NPI) approach exhibits uneven performance when the questions have different…

Current approaches to question answering rely on pre-trained language models (PLMs) like RoBERTa. This work challenges the existing question-answer encoding convention and explores finer representations. We begin with testing various…

Understanding complex biomolecular mechanisms requires multi-step reasoning across molecular interactions, signaling cascades, and metabolic pathways. While large language models(LLMs) show promise in such tasks, their application to…

Semantic parsing aims at mapping natural language utterances into structured meaning representations. In this work, we propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages. Given an…

Closed-book question answering (QA) requires a model to directly answer an open-domain question without access to any external knowledge. Prior work on closed-book QA either directly finetunes or prompts a pretrained language model (LM) to…

Large language models (LLMs) encode vast amounts of world knowledge but remain static once trained, making the timely integration of emerging facts prohibitively expensive via full retraining. Knowledge-editing techniques have thus emerged…

Concise reasoning in large language models seeks to generate only essential intermediate steps needed to arrive at a final answer, thereby alleviating issues of overthinking. Most proposed approaches hinge on carefully hand-crafted…

Executable semantic parsing is the task of converting natural language utterances into logical forms that can be directly used as queries to get a response. We build a transfer learning framework for executable semantic parsing. We show…

Semantic parsing aims at translating natural language (NL) utterances onto machine-interpretable programs, which can be executed against a real-world environment. The expensive annotation of utterance-program pairs has long been…

Question Answering over Knowledge Graph (KGQA) aims to seek answer entities for the natural language question from a large-scale Knowledge Graph~(KG). To better perform reasoning on KG, recent work typically adopts a pre-trained language…

Many AI applications rely on knowledge about a relevant real-world domain that is encoded by means of some logical knowledge base (KB). The most essential benefit of logical KBs is the opportunity to perform automatic reasoning to derive…

We propose a large language model explainability technique for obtaining faithful natural language explanations by grounding the explanations in a reasoning process. When converted to a sequence of tokens, the outputs of the reasoning…

Stepwise refinement of algebraic specifications is a well known formal methodology for program development. However, traditional notions of refinement based on signature morphisms are often too rigid to capture a number of relevant…

In this paper we examine the limitations of Large Language Models (LLMs) for complex reasoning tasks. Although recent works have started to employ formal languages as an intermediate representation for reasoning tasks, they often face…