Copertina

No-Worse Context-Aware Decoding: Preventing Neutral Regression in Context-Conditioned Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tao, Yufei, Agrawal, Ameeta
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences
di: Pokharel, Rhitabrat, et al.
Pubblicazione: (2025)

When Context Leads but Parametric Memory Follows in Large Language Models
di: Tao, Yufei, et al.
Pubblicazione: (2024)

"Lost-in-the-Later": Framework for Quantifying Contextual Grounding in Large Language Models
di: Tao, Yufei, et al.
Pubblicazione: (2025)

MTQ-Eval: Multilingual Text Quality Evaluation for Language Models
di: Pokharel, Rhitabrat, et al.
Pubblicazione: (2025)

Understanding Position Bias Effects on Fairness in Social Multi-Document Summarization
di: Olabisi, Olubusayo, et al.
Pubblicazione: (2024)

Pipelined Decoder for Efficient Context-Aware Text Generation
di: Huang, Zixian, et al.
Pubblicazione: (2025)

Cross-Lingual Activation Steering for Multilingual Language Models
di: Pokharel, Rhitabrat, et al.
Pubblicazione: (2026)

From Policy to Logic for Efficient and Interpretable Coverage Assessment
di: Pokharel, Rhitabrat, et al.
Pubblicazione: (2026)

Fair Summarization: Bridging Quality and Diversity in Extractive Summaries
di: Nezhad, Sina Bagheri, et al.
Pubblicazione: (2024)

Beyond Data Quantity: Key Factors Driving Performance in Multilingual Language Models
di: Nezhad, Sina Bagheri, et al.
Pubblicazione: (2024)

Mitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations
di: Dimgba, Martha O., et al.
Pubblicazione: (2025)

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective
di: Han, Seungwook, et al.
Pubblicazione: (2024)

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
di: Bi, Baolong, et al.
Pubblicazione: (2024)

Steering Multimodal Large Language Models Decoding for Context-Aware Safety
di: Liu, Zheyuan, et al.
Pubblicazione: (2025)

Parallel Context-of-Experts Decoding for Retrieval Augmented Generation
di: Corallo, Giulio, et al.
Pubblicazione: (2026)

Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgments
di: Scheinberg, Russell, et al.
Pubblicazione: (2025)

Correct-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMs
di: Shore, Amber, et al.
Pubblicazione: (2025)

The Impact of Model Scaling on Seen and Unseen Language Performance
di: Pokharel, Rhitabrat, et al.
Pubblicazione: (2025)

Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
di: Zhang, Yong, et al.
Pubblicazione: (2025)

Making a Long Story Short in Conversation Modeling
di: Tao, Yufei, et al.
Pubblicazione: (2024)

Context Memorization for Efficient Long Context Generation
di: Okoshi, Yasuyuki, et al.
Pubblicazione: (2026)

From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation
di: Guo, Zhihan, et al.
Pubblicazione: (2025)

In Context Learning and Reasoning for Symbolic Regression with Large Language Models
di: Sharlin, Samiha, et al.
Pubblicazione: (2024)

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
di: Lin, Gang, et al.
Pubblicazione: (2026)

Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation
di: Lau, Kwun Hang, et al.
Pubblicazione: (2026)

BERTs are Generative In-Context Learners
di: Samuel, David
Pubblicazione: (2024)

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
di: Wang, Zihao, et al.
Pubblicazione: (2024)

Context Engineering 2.0: The Context of Context Engineering
di: Hua, Qishuo, et al.
Pubblicazione: (2025)

Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding
di: Xiang, Yanzheng, et al.
Pubblicazione: (2026)

Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding
di: Zhou, Yigeng, et al.
Pubblicazione: (2026)

When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario Context
di: Noriega-Atala, Enrique, et al.
Pubblicazione: (2024)

OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs
di: Lee, Jaeseong, et al.
Pubblicazione: (2025)

AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment
di: Wang, Yixuan, et al.
Pubblicazione: (2026)

Context-Aware Content Moderation for German Newspaper Comments
di: Krejca, Felix, et al.
Pubblicazione: (2025)

Context-Aware Pragmatic Metacognitive Prompting for Sarcasm Detection
di: Iskandardinata, Michael, et al.
Pubblicazione: (2025)

Training Text-to-Molecule Models with Context-Aware Tokenization
di: Kim, Seojin, et al.
Pubblicazione: (2025)

Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering
di: Parekh, Jash Rajesh, et al.
Pubblicazione: (2026)

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
di: Tan, Hexiang, et al.
Pubblicazione: (2024)

IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
di: Shi, Dan, et al.
Pubblicazione: (2024)

Long-Context Generalization with Sparse Attention
di: Vasylenko, Pavlo, et al.
Pubblicazione: (2025)