Related papers: K-DeCore: Facilitating Knowledge Transfer in Conti…

Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods rely on task-specific strategies or…

Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…

Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions (NLQs) by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods either rely on employing…

Continuous Relation Extraction (CRE) aims to incrementally learn relation knowledge from a non-stationary stream of data. Since the introduction of new relational tasks can overshadow previously learned information, catastrophic forgetting…

Existing reinforcement learning methods for Chain-of-Thought reasoning suffer from two critical limitations. First, they operate as monolithic black boxes that provide undifferentiated reward signals, obscuring individual step contributions…

We present chain-of-knowledge (CoK), a novel framework that augments large language models (LLMs) by dynamically incorporating grounding information from heterogeneous sources. It results in more factual rationales and reduced hallucination…

Knowledge conflicts commonly arise across diverse sources, and their prevalence has increased with the advent of LLMs. When dealing with conflicts between multiple contexts, also known as \emph{inter-context knowledge conflicts}, LLMs are…

Continual self-supervised learning (CSSL) methods have gained increasing attention in remote sensing (RS) due to their capability to learn new tasks sequentially from continuous streams of unlabeled data. Existing CSSL methods, while…

Recent advances in knowledge distillation have emphasized the importance of decoupling different knowledge components. While existing methods utilize momentum mechanisms to separate task-oriented and distillation gradients, they overlook…

This paper targets e-commerce search relevance. While Large Language Models (LLMs) have demonstrated significant potential in this field, they often encounter performance bottlenecks in persistent 'corner cases' within complex industrial…

Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods…

Selecting the right knowledge is critical when using large language models (LLMs) to solve domain-specific data analysis tasks. However, most retrieval-augmented approaches rely primarily on lexical or embedding similarity, which is often a…

We introduce DecompSR, decomposed spatial reasoning, a large benchmark dataset (over 5m datapoints) and generation framework designed to analyse compositional spatial reasoning ability. The generation of DecompSR allows users to…

Dealing with context dependent knowledge has led to different formalizations of the notion of context. Among them is the Contextualized Knowledge Repository (CKR) framework, which is rooted in description logics but links on the reasoning…

Large Language Models (LMs) are known to encode world knowledge in their parameters as they pretrain on a vast amount of web corpus, which is often utilized for performing knowledge-dependent downstream tasks such as question answering,…

Large Language Models (LLMs) exhibit strong abilities in natural language understanding and generation, yet they struggle with knowledge-intensive reasoning. Structured Knowledge Graphs (KGs) provide an effective form of external knowledge…

Continual reinforcement learning (CRL) empowers RL agents with the ability to learn a sequence of tasks, accumulating knowledge learned in the past and using the knowledge for problemsolving or future task learning. However, existing…

Knowledge graphs (KGs) have emerged as a powerful paradigm for structuring and leveraging diverse real-world knowledge, which serve as a fundamental technology for enabling cognitive intelligence systems with advanced understanding and…

Large language models can exhibit emergent reasoning behaviors, often manifested as recurring lexical patterns (e.g., "wait," indicating verification). However, complex reasoning trajectories remain sparse in unconstrained sampling, and…

Large Language Models (LLMs) have exhibited impressive proficiency in various natural language processing (NLP) tasks, which involve increasingly complex reasoning. Knowledge reasoning, a primary type of reasoning, aims at deriving new…