Imagen de Portada

Beyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label Enhancement

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Ying, Qiao, Congyu, Geng, Xin, Xu, Ning
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Progressively Label Enhancement for Large Language Model Alignment
por: Liu, Biao, et al.
Publicado: (2024)

Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning
por: Qiao, Congyu, et al.
Publicado: (2024)

Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning
por: Deng, Jie, et al.
Publicado: (2026)

Negative-Prompt-driven Alignment for Generative Language Model
por: Qiao, Shiqi, et al.
Publicado: (2024)

Beyond Performance: Quantifying and Mitigating Label Bias in LLMs
por: Reif, Yuval, et al.
Publicado: (2024)

FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning
por: Zhang, Zhehao, et al.
Publicado: (2025)

Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
por: Yang, Junming, et al.
Publicado: (2025)

Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback
por: Xu, Hongshen, et al.
Publicado: (2024)

LLMs cannot spot math errors, even when allowed to peek into the solution
por: Srivatsa, KV Aditya, et al.
Publicado: (2025)

LLMs Struggle to Reject False Presuppositions when Misinformation Stakes are High
por: Sieker, Judith, et al.
Publicado: (2025)

Reasons to Reject? Aligning Language Models with Judgments
por: Xu, Weiwen, et al.
Publicado: (2023)

Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables
por: Geng, Xuzhao, et al.
Publicado: (2025)

Fast Best-of-N Decoding via Speculative Rejection
por: Sun, Hanshi, et al.
Publicado: (2024)

VRM: Teaching Reward Models to Understand Authentic Human Preferences
por: Liu, Biao, et al.
Publicado: (2026)

CrossTune: Black-Box Few-Shot Classification with Label Enhancement
por: Luo, Danqing, et al.
Publicado: (2024)

Beyond the Score: Uncertainty-Calibrated LLMs for Automated Essay Assessment
por: Karim, Ahmed, et al.
Publicado: (2025)

Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models
por: Liu, Biao, et al.
Publicado: (2025)

Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning
por: Xiong, Kai, et al.
Publicado: (2024)

ING-VP: MLLMs cannot Play Easy Vision-based Games Yet
por: Zhang, Haoran, et al.
Publicado: (2024)

Beyond Binary Gender Labels: Revealing Gender Biases in LLMs through Gender-Neutral Name Predictions
por: You, Zhiwen, et al.
Publicado: (2024)

General LLMs as Instructors for Domain-Specific LLMs: A Sequential Fusion Method to Integrate Extraction and Editing
por: Zhang, Xin, et al.
Publicado: (2024)

Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future
por: Wang, Yidong, et al.
Publicado: (2025)

LLMs cannot find reasoning errors, but can correct them given the error location
por: Tyen, Gladys, et al.
Publicado: (2023)

Augmenting In-Context-Learning in LLMs via Automatic Data Labeling and Refinement
por: Shtok, Joseph, et al.
Publicado: (2024)

Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation
por: Geng, Xiang, et al.
Publicado: (2025)

Jailbreaking LLMs via Semantically Relevant Nested Scenarios with Targeted Toxic Knowledge
por: Xu, Ning, et al.
Publicado: (2025)

Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs
por: Hu, Yi, et al.
Publicado: (2025)

LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models
por: Li, Xinxin, et al.
Publicado: (2025)

Show or Tell? Modeling the evolution of request-making in Human-LLM conversations
por: Zhu, Shengqi, et al.
Publicado: (2025)

Referential ambiguity and clarification requests: comparing human and LLM behaviour
por: Madge, Chris, et al.
Publicado: (2025)

Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing
por: Zhang, Yiqun, et al.
Publicado: (2025)

Synergizing LLMs with Global Label Propagation for Multimodal Fake News Detection
por: Hu, Shuguo, et al.
Publicado: (2025)

Aligning Reasoning LLMs for Materials Discovery with Physics-aware Rejection Sampling
por: Hyun, Lee, et al.
Publicado: (2025)

Beyond Surface Statistics: Robust Conformal Prediction for LLMs via Internal Representations
por: Wang, Yanli, et al.
Publicado: (2026)

Large Language Model probabilities cannot distinguish between possible and impossible language
por: Leivada, Evelina, et al.
Publicado: (2025)

GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs
por: Liu, Xiao, et al.
Publicado: (2024)

Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement
por: Zhan, Pengwei, et al.
Publicado: (2024)

Joint Enhancement of Relational Reasoning for Long-Context LLMs
por: Chen, Zhirui, et al.
Publicado: (2025)

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

What I cannot execute, I do not understand: Training and Evaluating LLMs on Program Execution Traces
por: Armengol-Estapé, Jordi, et al.
Publicado: (2025)