Copertina

Language Confusion Gate: Language-Aware Decoding Through Model Self-Distillation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Collin, Huang, Fei, Yuan, Chenhan, Lin, Junyang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention
di: Hu, Xiaomeng, et al.
Pubblicazione: (2025)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
di: Qiu, Zihan, et al.
Pubblicazione: (2025)

Finding Challenging Metaphors that Confuse Pretrained Language Models
di: Li, Yucheng, et al.
Pubblicazione: (2024)

Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model
di: Yuan, Chenhan, et al.
Pubblicazione: (2024)

Vision Language Models are Confused Tourists
di: Irawan, Patrick Amadeus, et al.
Pubblicazione: (2025)

Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
di: Zhao, Siyan, et al.
Pubblicazione: (2026)

Are Large Language Models True Healthcare Jacks-of-All-Trades? Benchmarking Across Health Professions Beyond Physician Exams
di: Luo, Zheheng, et al.
Pubblicazione: (2024)

Controlling Language Confusion in Multilingual LLMs
di: Lee, Nahyun, et al.
Pubblicazione: (2025)

Understanding and Mitigating Language Confusion in LLMs
di: Marchisio, Kelly, et al.
Pubblicazione: (2024)

CAST: Corpus-Aware Self-similarity Enhanced Topic modelling
di: Ma, Yanan, et al.
Pubblicazione: (2024)

Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
di: Nie, Ercong, et al.
Pubblicazione: (2025)

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models
di: Chen, Kecheng, et al.
Pubblicazione: (2026)

Self Speculative Decoding for Diffusion Large Language Models
di: Gao, Yifeng, et al.
Pubblicazione: (2025)

Self-Evolving Critique Abilities in Large Language Models
di: Tang, Zhengyang, et al.
Pubblicazione: (2025)

Language Models can Self-Lengthen to Generate Long Texts
di: Quan, Shanghaoran, et al.
Pubblicazione: (2024)

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding
di: Hoshino, Yuichiro, et al.
Pubblicazione: (2025)

Semantic Self-Distillation for Language Model Uncertainty
di: Phillips, Edward, et al.
Pubblicazione: (2026)

MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models
di: Ganesan, Mugilan, et al.
Pubblicazione: (2025)

Adversarial Confusion Attack: Disrupting Multimodal Large Language Models
di: Hoscilowicz, Jakub, et al.
Pubblicazione: (2025)

Component-Aware Self-Speculative Decoding in Hybrid Language Models
di: Borobia, Hector, et al.
Pubblicazione: (2026)

Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models
di: Xiang, Hao, et al.
Pubblicazione: (2024)

DSCD: Large Language Model Detoxification with Self-Constrained Decoding
di: Dong, Ming, et al.
Pubblicazione: (2025)

AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models
di: Zhu, Qin, et al.
Pubblicazione: (2025)

Disentangling Reasoning Tokens and Boilerplate Tokens For Language Model Fine-tuning
di: Ye, Ziang, et al.
Pubblicazione: (2024)

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

Skill-Conditioned Gated Self-Distillation for LLM Reasoning
di: Huang, Jiazhen, et al.
Pubblicazione: (2026)

GATES: Self-Distillation under Privileged Context with Consensus Gating
di: Stein, Alex, et al.
Pubblicazione: (2026)

Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules
di: Mohamed, Amr, et al.
Pubblicazione: (2025)

Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks
di: Everson, Kevin, et al.
Pubblicazione: (2024)

DAST: Difficulty-Aware Self-Training on Large Language Models
di: Xue, Boyang, et al.
Pubblicazione: (2025)

PLPP: Prompt Learning with Perplexity Is Self-Distillation for Vision-Language Models
di: Liu, Biao, et al.
Pubblicazione: (2024)

No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks
di: Hu, Gang, et al.
Pubblicazione: (2024)

Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation
di: Wang, Haoran, et al.
Pubblicazione: (2025)

FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation
di: Shum, KaShun, et al.
Pubblicazione: (2024)

Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
di: Zhang, Yanzhao, et al.
Pubblicazione: (2025)

Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding
di: Qu, Fanyi, et al.
Pubblicazione: (2024)

CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models
di: Liang, Yihao, et al.
Pubblicazione: (2026)

On-Policy Context Distillation for Language Models
di: Ye, Tianzhu, et al.
Pubblicazione: (2026)

Delta -- Contrastive Decoding Mitigates Text Hallucinations in Large Language Models
di: Huang, Cheng Peng, et al.
Pubblicazione: (2025)

You Only Cache Once: Decoder-Decoder Architectures for Language Models
di: Sun, Yutao, et al.
Pubblicazione: (2024)