12 papers
Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes
Luc Hazenoot, Zhaochun Ren, Amirhossein Zohrehvand
Existing measures of how much a text is about a concept read the surface of the text: dictionary word shares, topic proportions, embedding similarities. They score the words a text…
Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization
Yufei Chen, Zihan Wang, Yubao Tang +3
Multimodal generative retrieval formulates multimodal retrieval as discrete identifier generation, eliminating the need for explicit similarity search over external embeddings. Exi…
Reinforced Efficient Reasoning via Semantically Diverse Exploration
Ziqi Zhao, Zhaochun Ren, Jiahong Zou +9
Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs). Monte Carlo Tree Search (MCTS)-based extensio…
Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuning
Yukun Zhao, Lingyong Yan, Zhenyang Li +4
Large language models have achieved remarkable success in various tasks. However, it is challenging for them to learn new tasks incrementally due to catastrophic forgetting. Existi…
DiffuGR: Generative Document Retrieval with Diffusion Language Models
Xinpeng Zhao, Zhaochun Ren, Yukun Zhao +9
Generative retrieval (GR) reframes document retrieval as an end-to-end task of generating sequential document identifiers (DocIDs). Existing GR methods predominantly rely on left-t…
Evolution without Large Models: Training Language Model with Task Principles
Minghang Zhu, Shen Gao, Zhengliang Shi +5
A common training approach for language models involves using a large-scale language model to expand a human-provided dataset, which is subsequently used for model training.This me…