Imagen de Portada

Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Peng, Kerui, Li, Feifei, Fan, Xingyu, Que, Wenhui
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents
por: Li, Zihan, et al.
Publicado: (2026)

One Agent to Serve All: a Lite-Adaptive Stylized AI Assistant for Millions of Multi-Style Official Accounts
por: Fan, Xingyu, et al.
Publicado: (2025)

HiMeS: Hippocampus-inspired Memory System for Personalized AI Assistants
por: Li, Hailong, et al.
Publicado: (2026)

Teaching LLMs to Abstain via Fine-Grained Semantic Confidence Reward
por: An, Hao, et al.
Publicado: (2025)

Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain
por: Sayin, Burcu, et al.
Publicado: (2024)

Catch Me If You Can? Not Yet: LLMs Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors
por: Wang, Zhengxiang, et al.
Publicado: (2025)

LLM-REVal: Can We Trust LLM Reviewers Yet?
por: Li, Rui, et al.
Publicado: (2025)

Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method
por: Zhao, Yukun, et al.
Publicado: (2023)

FlowMind: Automatic Workflow Generation with LLMs
por: Zeng, Zhen, et al.
Publicado: (2024)

DepFlow: Disentangled Speech Generation to Mitigate Semantic Bias in Depression Detection
por: Li, Yuxin, et al.
Publicado: (2026)

Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs
por: Tan, Wenhui, et al.
Publicado: (2026)

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs
por: Lu, Yuxiao, et al.
Publicado: (2024)

Exploiting Emotion-Semantic Correlations for Empathetic Response Generation
por: Yang, Zhou, et al.
Publicado: (2024)

Measuring Teaching with LLMs
por: Hardy, Michael
Publicado: (2025)

Logic-Regularized Verifier Elicits Reasoning from LLMs
por: Wang, Xinyu, et al.
Publicado: (2026)

GPT-4V Cannot Generate Radiology Reports Yet
por: Jiang, Yuyang, et al.
Publicado: (2024)

PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator
por: Kong, Chuyi, et al.
Publicado: (2023)

How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization
por: Song, Shezheng, et al.
Publicado: (2025)

Beyond the Binary: Capturing Diverse Preferences With Reward Regularization
por: Padmakumar, Vishakh, et al.
Publicado: (2024)

Capturing Bias Diversity in LLMs
por: Gosavi, Purva Prasad, et al.
Publicado: (2024)

To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation
por: Zhang, Yitong, et al.
Publicado: (2026)

The Price of Format: Diversity Collapse in LLMs
por: Yun, Longfei, et al.
Publicado: (2025)

Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?
por: Addepalli, Sravanti, et al.
Publicado: (2024)

Large Language Models for Biomedical Text Simplification: Promising But Not There Yet
por: Li, Zihao, et al.
Publicado: (2024)

Self-Improving Customer Review Response Generation Based on LLMs
por: Azov, Guy, et al.
Publicado: (2024)

LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought
por: Jiang, Zhuoxuan, et al.
Publicado: (2024)

Consultant Decoding: Yet Another Synergistic Mechanism
por: Ding, Chuanghao, et al.
Publicado: (2025)

Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild
por: Wang, Jiatai, et al.
Publicado: (2025)

Semantic-guided Diverse Decoding for Large Language Model
por: Shi, Weijie, et al.
Publicado: (2025)

Is Open-Source There Yet? A Comparative Study on Commercial and Open-Source LLMs in Their Ability to Label Chest X-Ray Reports
por: Dorfner, Felix J., et al.
Publicado: (2024)

FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs
por: Bao, Forrest Sheng, et al.
Publicado: (2024)

CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agent
por: Fan, Fengxiao, et al.
Publicado: (2025)

Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs
por: Parmar, Mihir, et al.
Publicado: (2024)

Why Synthetic Isn't Real Yet: A Diagnostic Framework for Contact Center Dialogue Generation
por: Devanathan, Rishikesh, et al.
Publicado: (2025)

AgentInstruct: Toward Generative Teaching with Agentic Flows
por: Mitra, Arindam, et al.
Publicado: (2024)

Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition
por: Wang, Peng, et al.
Publicado: (2026)

CauScientist: Teaching LLMs to Respect Data for Causal Discovery
por: Peng, Bo, et al.
Publicado: (2026)

Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning
por: Li, Yangning, et al.
Publicado: (2025)

LLMs Can Teach Themselves to Better Predict the Future
por: Turtel, Benjamin, et al.
Publicado: (2025)

Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements
por: Li, Ming, et al.
Publicado: (2024)