Copertina

Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gekhman, Zorik, Yona, Gal, Aharoni, Roee, Eyal, Matan, Feder, Amir, Reichart, Roi, Herzig, Jonathan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
di: Gekhman, Zorik, et al.
Pubblicazione: (2026)

Can LLMs Learn Macroeconomic Narratives from Social Media?
di: Gueta, Almog, et al.
Pubblicazione: (2024)

Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs
di: Peisakhovsky, Yehonatan, et al.
Pubblicazione: (2025)

Inside-Out: Hidden Factual Knowledge in LLMs
di: Gekhman, Zorik, et al.
Pubblicazione: (2025)

Confidence Improves Self-Consistency in LLMs
di: Taubenfeld, Amir, et al.
Pubblicazione: (2025)

Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers
di: Yona, Gal, et al.
Pubblicazione: (2024)

Why Fine-Tuning Encourages Hallucinations and How to Fix It
di: Kaplan, Guy, et al.
Pubblicazione: (2026)

Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
di: Calderon, Nitay, et al.
Pubblicazione: (2026)

HACK: Hallucinations Along Certainty and Knowledge Axes
di: Simhi, Adi, et al.
Pubblicazione: (2025)

Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?
di: Yona, Gal, et al.
Pubblicazione: (2024)

Multilingual Instruction Tuning With Just a Pinch of Multilinguality
di: Shaham, Uri, et al.
Pubblicazione: (2024)

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
di: Orgad, Hadas, et al.
Pubblicazione: (2024)

Keep Guessing? When Considering Inference Scaling, Mind the Baselines
di: Yona, Gal, et al.
Pubblicazione: (2024)

Measuring the Robustness of NLP Models to Domain Shifts
di: Calderon, Nitay, et al.
Pubblicazione: (2023)

NL-Eye: Abductive NLI for Images
di: Ventura, Mor, et al.
Pubblicazione: (2024)

Evaluating Alignment of Behavioral Dispositions in LLMs
di: Taubenfeld, Amir, et al.
Pubblicazione: (2026)

mFACE: Multilingual Summarization with Factual Consistency Evaluation
di: Aharoni, Roee, et al.
Pubblicazione: (2022)

Hallucinations Undermine Trust; Metacognition is a Way Forward
di: Yona, Gal, et al.
Pubblicazione: (2026)

Representation Surgery: Theory and Practice of Affine Steering
di: Singh, Shashwat, et al.
Pubblicazione: (2024)

Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs
di: Ifergan, Maxim, et al.
Pubblicazione: (2024)

On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs
di: Calderon, Nitay, et al.
Pubblicazione: (2024)

Leveraging NTPs for Efficient Hallucination Detection in VLMs
di: Azachi, Ofir, et al.
Pubblicazione: (2025)

DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs
di: Cattan, Arie, et al.
Pubblicazione: (2025)

DoubleDipper: Improving Long-Context LLMs via Context Recycling
di: Cattan, Arie, et al.
Pubblicazione: (2024)

A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains
di: Jacovi, Alon, et al.
Pubblicazione: (2024)

The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth
di: Lissak, Shir, et al.
Pubblicazione: (2024)

Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs
di: Simhi, Adi, et al.
Pubblicazione: (2024)

Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning
di: Dymkiewicz, Kajetan, et al.
Pubblicazione: (2025)

AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation
di: Nakash, Itay, et al.
Pubblicazione: (2025)

Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models
di: Ventura, Mor, et al.
Pubblicazione: (2023)

The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs
di: Calderon, Nitay, et al.
Pubblicazione: (2025)

TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools
di: Caciularu, Avi, et al.
Pubblicazione: (2024)

SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning
di: Chen, Yijie, et al.
Pubblicazione: (2026)

A Systematic Review of NLP for Dementia -- Tasks, Datasets and Opportunities
di: Peled-Cohen, Lotem, et al.
Pubblicazione: (2024)

Systematic Biases in LLM Simulations of Debates
di: Taubenfeld, Amir, et al.
Pubblicazione: (2024)

Distributional reasoning in LLMs: Parallel reasoning processes in multi-hop reasoning
di: Shalev, Yuval, et al.
Pubblicazione: (2024)

LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals
di: Toker, Gilat, et al.
Pubblicazione: (2026)

Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance
di: Nahum, Omer, et al.
Pubblicazione: (2024)

Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models
di: Khadangi, Afshin, et al.
Pubblicazione: (2025)

SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge
di: Haas, Lukas, et al.
Pubblicazione: (2025)