:: Library Catalog

Imagen de Portada

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Qingru, Yu, Xiaodong, Singh, Chandan, Liu, Xiaodong, Liu, Liyuan, Gao, Jianfeng, Zhao, Tuo, Roth, Dan, Cheng, Hao
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	https://arxiv.org/abs/2409.10790
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
por: Zhang, Qingru, et al.
Publicado: (2023)

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks
por: Yu, Xiaodong, et al.
Publicado: (2023)

Vector-ICL: In-context Learning with Continuous Vector Representations
por: Zhuang, Yufan, et al.
Publicado: (2024)

Text Generation Beyond Discrete Token Sampling
por: Zhuang, Yufan, et al.
Publicado: (2025)

Learning a Decision Tree Algorithm with Transformers
por: Zhuang, Yufan, et al.
Publicado: (2024)

Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
por: Chen, Yanda, et al.
Publicado: (2024)

Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts
por: Zhang, Zeliang, et al.
Publicado: (2024)

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
por: Ge, Suyu, et al.
Publicado: (2023)

Training Large Reasoning Models Efficiently via Progressive Thought Encoding
por: Zhang, Zeliang, et al.
Publicado: (2026)

Test-time Recursive Thinking: Self-Improvement without External Feedback
por: Zhuang, Yufan, et al.
Publicado: (2026)

GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM
por: Kang, Hao, et al.
Publicado: (2024)

SAS: Simulated Attention Score
por: Zheng, Chuanyang, et al.
Publicado: (2025)

Language Models as Inductive Reasoners
por: Yang, Zonglin, et al.
Publicado: (2022)

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass
por: Chen, Tong, et al.
Publicado: (2024)

DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entries
por: Liu, Xiaodong
Publicado: (2024)

FaithRL: Learning to Reason Faithfully through Step-Level Faithfulness Maximization
por: Gui, Runquan, et al.
Publicado: (2026)

Detoxification for LLM: From Dataset Itself
por: Shao, Wei, et al.
Publicado: (2026)

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
por: Sun, Chung-En, et al.
Publicado: (2024)

ReasonAgain: Using Extractable Symbolic Programs to Evaluate Mathematical Reasoning
por: Yu, Xiaodong, et al.
Publicado: (2024)

Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding
por: Feng, Qi, et al.
Publicado: (2025)

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
por: Feng, Mingqian, et al.
Publicado: (2026)

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
por: Song, Jialin, et al.
Publicado: (2026)

Where Fake Citations Are Made: Tracing Field-Level Hallucination to Specific Neurons in LLMs
por: Chen, Yuefei, et al.
Publicado: (2026)

GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradients
por: Kazama, Kentaro, et al.
Publicado: (2026)

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
por: Bao, Yuntai, et al.
Publicado: (2026)

AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation
por: Fang, Yixiong, et al.
Publicado: (2025)

Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
por: Gong, Linyuan, et al.
Publicado: (2023)

Rethinking Interpretability in the Era of Large Language Models
por: Singh, Chandan, et al.
Publicado: (2024)

Evaluating LLMs on Chinese Topic Constructions: A Research Proposal Inspired by Tian et al. (2024)
por: Yang, Xiaodong
Publicado: (2025)

Predicting Where Steering Vectors Succeed
por: Billa, Jayadev
Publicado: (2026)

Knocking-Heads Attention
por: Zhou, Zhanchao, et al.
Publicado: (2025)

MEETING DELEGATE: Benchmarking LLMs on Attending Meetings on Our Behalf
por: Hu, Lingxiang, et al.
Publicado: (2025)

Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
por: Tian, Changyuan, et al.
Publicado: (2026)

Conflicts in Texts: Data, Implications and Challenges
por: Liu, Siyi, et al.
Publicado: (2025)

Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks
por: Štorek, Adam, et al.
Publicado: (2025)

Interpretable Next-token Prediction via the Generalized Induction Head
por: Kim, Eunji, et al.
Publicado: (2024)

H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables
por: Abhyankar, Nikhil, et al.
Publicado: (2024)

Steering LLMs toward Korean Local Speech: Iterative Refinement Framework for Faithful Dialect Translation
por: Park, Keunhyeung, et al.
Publicado: (2025)

Does a Global Perspective Help Prune Sparse MoEs Elegantly?
por: Zhang, Zeliang, et al.
Publicado: (2026)

Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks
por: Wang, Zheng, et al.
Publicado: (2024)