Copertina

Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Badhe, Sanket, Shah, Deep
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Information Retrieval
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms
di: Shah, Deep, et al.
Pubblicazione: (2026)

CROP: Token-Efficient Reasoning in Large Language Models via Regularized Prompt Optimization
di: Shah, Deep, et al.
Pubblicazione: (2026)

NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval
di: Zeighami, Sepanta, et al.
Pubblicazione: (2024)

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model
di: Sinhababu, Nilanjan, et al.
Pubblicazione: (2024)

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

Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking
di: Samarinas, Chris, et al.
Pubblicazione: (2025)

Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications
di: Badhe, Sanket, et al.
Pubblicazione: (2026)

Passage-specific Prompt Tuning for Passage Reranking in Question Answering with Large Language Models
di: Wu, Xuyang, et al.
Pubblicazione: (2024)

REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models
di: Gupta, Ambuje, et al.
Pubblicazione: (2024)

Optimized Quran Passage Retrieval Using an Expanded QA Dataset and Fine-Tuned Language Models
di: Basem, Mohamed, et al.
Pubblicazione: (2024)

Few-Shot Prompting for Extractive Quranic QA with Instruction-Tuned LLMs
di: Basem, Mohamed, et al.
Pubblicazione: (2025)

When Fine-Tuning Fails: Lessons from MS MARCO Passage Ranking
di: Pande, Manu, et al.
Pubblicazione: (2025)

The Silent Vote: Improving Zero-Shot LLM Reliability by Aggregating Semantic Neighborhoods
di: Badhe, Sanket, et al.
Pubblicazione: (2026)

Learning User Interests via Reasoning and Distillation for Cross-Domain News Recommendation
di: Zhu, Mengdan, et al.
Pubblicazione: (2026)

LLM, Reporting In! Medical Information Extraction Across Prompting, Fine-tuning and Post-correction
di: Belmadani, Ikram, et al.
Pubblicazione: (2025)

DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation
di: Abdallah, Abdelrahman, et al.
Pubblicazione: (2025)

Parametric Retrieval Augmented Generation
di: Su, Weihang, et al.
Pubblicazione: (2025)

Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning
di: Samarinas, Chris, et al.
Pubblicazione: (2026)

Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models
di: Cong, Youan, et al.
Pubblicazione: (2024)

DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Search
di: Lupart, Simon, et al.
Pubblicazione: (2024)

Dynamic and Parametric Retrieval-Augmented Generation
di: Su, Weihang, et al.
Pubblicazione: (2025)

LEMUR: A Corpus for Robust Fine-Tuning of Multilingual Law Embedding Models for Retrieval
di: Ahmadi, Narges Baba, et al.
Pubblicazione: (2026)

Are Longer Prompts Always Better? Prompt Selection in Large Language Models for Recommendation Systems
di: Kusano, Genki, et al.
Pubblicazione: (2024)

Quantifying and Mitigating Selection Bias in LLMs: A Transferable LoRA Fine-Tuning and Efficient Majority Voting Approach
di: Guda, Blessed, et al.
Pubblicazione: (2025)

Automating Research Synthesis with Domain-Specific Large Language Model Fine-Tuning
di: Susnjak, Teo, et al.
Pubblicazione: (2024)

PairDistill: Pairwise Relevance Distillation for Dense Retrieval
di: Huang, Chao-Wei, et al.
Pubblicazione: (2024)

Domain Fine-Tuning vs. Retrieval-Augmented Generation for Medical Multiple-Choice Question Answering: A Controlled Comparison at the 4B-Parameter Scale
di: Buskila, Avi-ad Avraam
Pubblicazione: (2026)

Distilling Reasoning Without Knowledge: A Framework for Reliable LLMs
di: Kietkajornrit, Auksarapak, et al.
Pubblicazione: (2026)

Understanding Parametric Knowledge Injection in Retrieval-Augmented Generation
di: Tang, Minghao, et al.
Pubblicazione: (2025)

SRR-Judge: Step-Level Rating and Refinement for Enhancing Search-Integrated Reasoning in Search Agents
di: Zhang, Chen, et al.
Pubblicazione: (2026)

Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillation
di: Yang, Eugene, et al.
Pubblicazione: (2024)

Does Knowledge Distillation Matter for Large Language Model based Bundle Generation?
di: Feng, Kaidong, et al.
Pubblicazione: (2025)

Best Practices for Distilling Large Language Models into BERT for Web Search Ranking
di: Ye, Dezhi, et al.
Pubblicazione: (2024)

Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025
di: Augenstein, Isabelle
Pubblicazione: (2026)

Distillation for Multilingual Information Retrieval
di: Yang, Eugene, et al.
Pubblicazione: (2024)

Fine-Tuning Large Language Models and Evaluating Retrieval Methods for Improved Question Answering on Building Codes
di: Aqib, Mohammad, et al.
Pubblicazione: (2025)

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings
di: Ma, Yubo, et al.
Pubblicazione: (2025)

An Alternative to FLOPS Regularization to Effectively Productionize SPLADE-Doc
di: Porco, Aldo, et al.
Pubblicazione: (2025)

UNH at CheckThat! 2025: Fine-tuning Vs Prompting in Claim Extraction
di: Wilder, Joe, et al.
Pubblicazione: (2025)

INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning
di: Zhu, Yutao, et al.
Pubblicazione: (2024)