Related papers: Knowledge Integration Decay in Search-Augmented Re…
Knowledge erasure in large language models (LLMs) is important for ensuring compliance with data and AI regulations, safeguarding user privacy, mitigating bias, and misinformation. Existing unlearning methods aim to make the process of…
Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access broader knowledge sources, yet factual inconsistencies persist due to noise in retrieved documents-even with advanced retrieval methods. We demonstrate that…
Knowledge embeddings (KE) represent a knowledge graph (KG) by embedding entities and relations into continuous vector spaces. Existing methods are mainly structure-based or description-based. Structure-based methods learn representations…
Large language models (LLMs) typically enhance their performance through either the retrieval of semantically similar information or the improvement of their reasoning capabilities. However, a significant challenge remains in effectively…
Transformer-based models such as BERT and E5 have significantly advanced text embedding by capturing rich contextual representations. However, many complex real-world queries require sophisticated reasoning to retrieve relevant documents…
Large Language Models (LLMs) have achieved impressive results across numerous domains, yet they experience notable deficiencies in legal question-answering tasks. LLMs often generate generalized responses that lack the logical specificity…
Query expansion (QE) enhances retrieval by incorporating relevant terms, with large language models (LLMs) offering an effective alternative to traditional rule-based and statistical methods. However, LLM-based QE suffers from a fundamental…
Large Language Models (LLMs) excel at many reasoning tasks but struggle with knowledge-intensive queries due to their inability to dynamically access up-to-date or domain-specific information. Retrieval-Augmented Generation (RAG) has…
Reinforcement learning with verifiable rewards improves reasoning in large language models (LLMs), but many methods still rely on large human-labeled datasets. While self-play reduces this dependency, it often lacks explicit planning and…
Large language models (LLMs) learn contextual embeddings that capture rich semantic information, yet they often overlook structured lexical knowledge such as word senses and relationships. Prior work has shown that incorporating sense…
There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding. Existing studies primarily focus on prompting powerful, closed-source models to generate seed training data followed by…
Large Language Models (LLMs) have shown promising performance in text-to-SQL, which involves translating natural language questions into SQL queries. However, current text-to-SQL LLMs are computationally expensive and challenging to deploy…
Large language models (LLMs) exhibit superior performance on various natural language tasks, but they are susceptible to issues stemming from outdated data and domain-specific limitations. In order to address these challenges, researchers…
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…
Large vision-language models (VLMs) frequently suffer from hallucinations, generating content that is inconsistent with visual inputs. Existing methods typically address this problem through post-hoc filtering, additional training…
Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning…
Knowledge Editing (KE) aims to adjust a Large Language Model's (LLM) internal representations and parameters to correct inaccuracies and improve output consistency without incurring the computational expense of re-training the entire model.…
In logic-based approaches to reasoning tasks such as Recognizing Textual Entailment (RTE), it is important for a system to have a large amount of knowledge data. However, there is a tradeoff between adding more knowledge data for improved…
Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable…
Large Language Models (LLMs) have shown impressive capabilities across various tasks but remain vulnerable to meticulously crafted jailbreak attacks. In this paper, we identify a critical safety gap: while LLMs are adept at detecting…