paper-with-me

Papers

The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models

2023-05-23 · Shuo Zhang, Liangming Pan, Junzhou Zhao, William Yang Wang

Large language models often necessitate grounding on external knowledge to generate faithful and reliable answers. Yet even with the correct groundings in the reference, they can ignore them and rely on wrong groundings or their inherent biases to hallucinate when users, being largely unaware of the specifics of the stored information, pose questions that might not directly correlate with the retrieved groundings. In this work, we formulate this knowledge alignment problem and introduce MixAlign, a framework that interacts with both the human user and the knowledge base to obtain and integrate clarifications on how the user question relates to the stored information. MixAlign employs a language model to achieve automatic knowledge alignment and, if necessary, further enhances this alignment through human user clarifications. Experimental results highlight the crucial role of knowledge alignment in boosting model performance and mitigating hallucination, with improvements noted up to 22.2% and 27.1% respectively. We also demonstrate the effectiveness of MixAlign in improving knowledge alignment by producing high-quality, user-centered clarifications.

📄 PDF Abstract BibTeX arXiv:2305.13669

Code (1)

shuozhangxjtu/mixalign 공식 구현

Tasks

HallucinationLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
BASE 설명 없음

Similar Papers 제목 키워드 기반

Integrating knowledge bases to improve coreference and bridging resolution for the chemical domain

2024-04-16 · Pengcheng Lu, Massimo Poesio

Resolving coreference and bridging relations in chemical patents is important for better understanding the precise chemical process, where chemical domain knowledge is very critical. We proposed an approach incorporating…

Chemical ProcessMulti-Task Learning

AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering

2026-05-17 · Taolin Zhang, Dongyang Li, Chen Chen, Qizhou Chen 외 arxiv

Despite substantial advances in large language models (LLMs), generating factually consistent responses for knowledge-intensive question answering remains challenging. These difficulties are primarily due to hallucinatio…

Question Answering

Mitigating Safety Tax via Distribution-Grounded Refinement in Large Reasoning Models

2026-02-02 · Yingsha Xie, Tiansheng Huang, Enneng Yang, Rui Min 외 arxiv

Safety alignment incurs safety tax that perturbs a large reasoning model's (LRM) general reasoning ability. Existing datasets used for safety alignment for an LRM are usually constructed by distilling safety reasoning tr…

Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships

2024-07-17 · Angie Boggust, Hyemin Bang, Hendrik Strobelt, Arvind Satyanarayan

While interpretability methods identify a model's learned concepts, they overlook the relationships between concepts that make up its abstractions and inform its ability to generalize to new data. To assess whether model…

Benchmarking

Knowledge Verification to Nip Hallucination in the Bud

2024-01-19 · Fanqi Wan, Xinting Huang, Leyang Cui, Xiaojun Quan 외

While large language models (LLMs) have demonstrated exceptional performance across various tasks following human alignment, they may still generate responses that sound plausible but contradict factual knowledge, a phen…

HallucinationWorld Knowledge