Buchumschlag

Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Madhwal, Dhruv, Zhang, Lyuxin David, Roth, Dan, Wolfson, Tomer, Gupta, Vivek
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

R-Tuning: Instructing Large Language Models to Say `I Don't Know'
von: Zhang, Hanning, et al.
Veröffentlicht: (2023)

What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say "I Don't Know"
von: Lee, Joosung, et al.
Veröffentlicht: (2026)

What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts
von: Yang, Chenyang, et al.
Veröffentlicht: (2025)

Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG
von: Chen, Xinxi, et al.
Veröffentlicht: (2024)

What Language Models Know But Don't Say: Non-Generative Prior Extraction for Generalization
von: Rezaeimanesh, Sara, et al.
Veröffentlicht: (2026)

I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token
von: Cohen, Roi, et al.
Veröffentlicht: (2024)

Don't Say No: Jailbreaking LLM by Suppressing Refusal
von: Zhou, Yukai, et al.
Veröffentlicht: (2024)

Can AI Assistants Know What They Don't Know?
von: Cheng, Qinyuan, et al.
Veröffentlicht: (2024)

Do Retrieval Augmented Language Models Know When They Don't Know?
von: Zhou, Youchao, et al.
Veröffentlicht: (2025)

Reasoning Models Don't Always Say What They Think
von: Chen, Yanda, et al.
Veröffentlicht: (2025)

Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing
von: Zhao, Raoyuan, et al.
Veröffentlicht: (2025)

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
von: Mei, Zhiting, et al.
Veröffentlicht: (2025)

EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline
von: Chen, Peter Baile, et al.
Veröffentlicht: (2025)

Large Language Models Must Be Taught to Know What They Don't Know
von: Kapoor, Sanyam, et al.
Veröffentlicht: (2024)

Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
von: Ren, Jingyi, et al.
Veröffentlicht: (2026)

Do LLMs Really Know What They Don't Know? Internal States Mainly Reflect Knowledge Recall Rather Than Truthfulness
von: Cheang, Chi Seng, et al.
Veröffentlicht: (2025)

SAGE: Structure Aware Graph Expansion for Retrieval of Heterogeneous Data
von: Titiya, Prasham, et al.
Veröffentlicht: (2026)

Generating Tables from the Parametric Knowledge of Language Models
von: Berkovitch, Yevgeni, et al.
Veröffentlicht: (2024)

Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding
von: Im, Eun Woo, et al.
Veröffentlicht: (2026)

When You Don't Know the Answer, Say So
Veröffentlicht: (2024)

Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models
von: Young, Richard J.
Veröffentlicht: (2026)

When Words Don't Mean What They Say: Figurative Understanding in Bengali Idioms
von: Sakhawat, Adib, et al.
Veröffentlicht: (2026)

Don't Delay: Help Parents Find Language Development Resources
von: Arnold, Renea, et al.
Veröffentlicht: (2005)

Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations
von: Deng, Yang, et al.
Veröffentlicht: (2024)

Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration
von: Feng, Shangbin, et al.
Veröffentlicht: (2024)

Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty
von: Shi, Zeyu, et al.
Veröffentlicht: (2025)

EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs
von: Yeom, Jewon, et al.
Veröffentlicht: (2026)

"Knowing When You Don't Know": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation
von: Thakur, Nandan, et al.
Veröffentlicht: (2023)

No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning
von: Rajgaria, Abhishek, et al.
Veröffentlicht: (2025)

The Detection-Extraction Gap: Models Know the Answer Before They Can Say It
von: Wang, Hanyang, et al.
Veröffentlicht: (2026)

Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell
von: Lu, Taiming, et al.
Veröffentlicht: (2024)

Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing
von: Yang, Diji, et al.
Veröffentlicht: (2025)

Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models
von: Yu, Zhiyuan, et al.
Veröffentlicht: (2024)

Prompting Science Report 4: Playing Pretend: Expert Personas Don't Improve Factual Accuracy
von: Basil, Savir, et al.
Veröffentlicht: (2025)

You Don't Need Prompt Engineering Anymore: The Prompting Inversion
von: Khan, Imran
Veröffentlicht: (2025)

Why Don't You Know? Evaluating the Impact of Uncertainty Sources on Uncertainty Quantification in LLMs
von: Goloburda, Maiya, et al.
Veröffentlicht: (2026)

When Robots Should Say "I Don't Know": Benchmarking Abstention in Embodied Question Answering
von: Wu, Tao, et al.
Veröffentlicht: (2025)

Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users
von: Balepur, Nishant, et al.
Veröffentlicht: (2026)

LLM-Symbolic Integration for Robust Temporal Tabular Reasoning
von: Kulkarni, Atharv, et al.
Veröffentlicht: (2025)

Don't Throw Away Your Pretrained Model
von: Feng, Shangbin, et al.
Veröffentlicht: (2025)