Copertina

Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yin, Qingyu, He, Xuzheng, Deng, Luoao, Leong, Chak Tou, Wang, Fan, Yan, Yanzhao, Shen, Xiaoyu, Zhang, Qiang
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Induction Head Toxicity Mechanistically Explains Repetition Curse in Large Language Models
di: Wang, Shuxun, et al.
Pubblicazione: (2025)

Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
di: Leong, Chak Tou, et al.
Pubblicazione: (2025)

Probing the Difficulty Perception Mechanism of Large Language Models
di: Lee, Sunbowen, et al.
Pubblicazione: (2025)

StableMask: Refining Causal Masking in Decoder-only Transformer
di: Yin, Qingyu, et al.
Pubblicazione: (2024)

Constrain Alignment with Sparse Autoencoders
di: Yin, Qingyu, et al.
Pubblicazione: (2024)

Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
di: Leong, Chak Tou, et al.
Pubblicazione: (2026)

STeCa: Step-level Trajectory Calibration for LLM Agent Learning
di: Wang, Hanlin, et al.
Pubblicazione: (2025)

E2CL: Exploration-based Error Correction Learning for Embodied Agents
di: Wang, Hanlin, et al.
Pubblicazione: (2024)

Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
di: Yang, Wang, et al.
Pubblicazione: (2025)

No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks
di: Leong, Chak Tou, et al.
Pubblicazione: (2024)

Evaluating Parameter Efficient Methods for RLVR
di: Yin, Qingyu, et al.
Pubblicazione: (2025)

Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents
di: Wang, Hanlin, et al.
Pubblicazione: (2026)

Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue
di: Wang, Jian, et al.
Pubblicazione: (2024)

Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
di: Wang, Jian, et al.
Pubblicazione: (2025)

TokenSkip: Controllable Chain-of-Thought Compression in LLMs
di: Xia, Heming, et al.
Pubblicazione: (2025)

SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution
di: Wang, Hanlin, et al.
Pubblicazione: (2025)

Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback
di: Wang, Jiashuo, et al.
Pubblicazione: (2024)

Deeper Insights into Learning Performance of Stochastic Configuration Networks
di: Yan, Xiufeng, et al.
Pubblicazione: (2024)

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
di: Yin, Qingyu, et al.
Pubblicazione: (2025)

Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning
di: Tan, Qingyu, et al.
Pubblicazione: (2023)

Probing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic Stylistics
di: Wang, Jiashuo, et al.
Pubblicazione: (2026)

Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
di: Xia, Heming, et al.
Pubblicazione: (2025)

Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
di: Lee, Chungpa, et al.
Pubblicazione: (2026)

Boosting Deep Ensembles with Learning Rate Tuning
di: Jin, Hongpeng, et al.
Pubblicazione: (2024)

Protein as a Second Language for LLMs
di: Chen, Xinhui, et al.
Pubblicazione: (2025)

KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization
di: Song, Mingbo, et al.
Pubblicazione: (2025)

Order-Independence Without Fine Tuning
di: McIlroy-Young, Reid, et al.
Pubblicazione: (2024)

No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
di: Kazdan, Joshua, et al.
Pubblicazione: (2025)

ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking
di: Cai, Yuzheng, et al.
Pubblicazione: (2025)

Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
di: Li, Yibo, et al.
Pubblicazione: (2026)

FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension
di: Liu, Junzhuo, et al.
Pubblicazione: (2024)

Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning
di: Wang, Futing, et al.
Pubblicazione: (2026)

Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates
di: Prashant, Parjanya Prajakta, et al.
Pubblicazione: (2026)

Achieving Tool Calling Functionality in LLMs Using Only Prompt Engineering Without Fine-Tuning
di: He, Shengtao
Pubblicazione: (2024)

On-Policy Supervised Fine-Tuning for Efficient Reasoning
di: Zhao, Anhao, et al.
Pubblicazione: (2026)

Efficient Fine-Tuning of Large Language Models for Automated Medical Documentation
di: Leong, Hui Yi, et al.
Pubblicazione: (2024)

Fine-Tuned In-Context Learners for Efficient Adaptation
di: Bornschein, Jorg, et al.
Pubblicazione: (2025)

Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN
di: Li, Pengxiang, et al.
Pubblicazione: (2024)

MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
di: Jiang, Ting, et al.
Pubblicazione: (2024)

In-Context Learning and Fine-Tuning GPT for Argument Mining
di: Cabessa, Jérémie, et al.
Pubblicazione: (2024)