Papers with APP
OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)
Copied to clipboard
Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou
| Challenge: | Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs. |
| Approach: | They propose a framework that integrates dialogue, reasoning, and personalized recommendation. |
| Outcome: | Experiments across public benchmarks show state-of-the-art performance. |
Ask Patients with Patience: Enabling LLMs for Human-Centric Medical Dialogue with Grounded Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | a shortage of medical doctors limits access to timely and reliable healthcare . authors propose a multi-turn LLM-based medical assistant for medical inquiries . |
| Approach: | They propose a multi-turn LLM-based medical assistant that asks patients with patience . they compare it with SOTA one-shot and multi-turned LLMs to evaluate its performance . |
| Outcome: | The proposed medical assistant improves diagnostic accuracy, reduces uncertainty and enhances user experience. |
Evaluating Sparse Autoencoders for Monosemantic Representation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Sparse autoencoders (SAEs) have been proposed to mitigate polysemanticity, where neurons activate for multiple unrelated concepts. |
| Approach: | They propose a sparse autoencoder to transform dense activations into sparser, more interpretable features by transforming them into sparses. |
| Outcome: | The proposed model reduces polysemanticity and achieves higher concept separability. |
Exploring and Controlling Diversity in LLM-Agent Conversation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Adaptive Prompt Pruning (APP) allows users to control diversity via a single parameter. |
| Approach: | They propose a method that allows users to control diversity via a single parameter . they propose to modularize the utterance generation prompt and reduce contextual information . |
| Outcome: | The proposed method reduces diversity in dialogues over long-term simulations by reducing contextual information. |
The Dominance of Text Space: Unveiling the Asymmetric Nature of Cross-Modal Alignment in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for cross-modal alignment assume a symmetric interaction between visual and textual modalities, implying that both spaces adapt to each other. |
| Approach: | They propose a method that regularizes the projector to maintain the geometric structure of the text embedding space via spectral filtering. |
| Outcome: | The proposed method preserves the LLM’s inherent linguistic capabilities and reduces object hallucination significantly better than standard fine-tuning methods. |