Copertina

DEPTH: Discourse Education through Pre-Training Hierarchically

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bamberger, Zachary, Glick, Ofek, Baskin, Chaim, Belinkov, Yonatan
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

Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods
di: Blau, Tsachi, et al.
Pubblicazione: (2024)

ContraSim -- Analyzing Neural Representations Based on Contrastive Learning
di: Rahamim, Adir, et al.
Pubblicazione: (2023)

Fast Forwarding Low-Rank Training
di: Rahamim, Adir, et al.
Pubblicazione: (2024)

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
di: Yu, Zeping, et al.
Pubblicazione: (2025)

MATCH: Task-Driven Code Evaluation through Contrastive Learning
di: Ghoummaid, Marah, et al.
Pubblicazione: (2025)

Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
di: Iskander, Shadi, et al.
Pubblicazione: (2024)

Concept-Best-Matching: Evaluating Compositionality in Emergent Communication
di: Carmeli, Boaz, et al.
Pubblicazione: (2024)

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

REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space
di: Ashuach, Tomer, et al.
Pubblicazione: (2024)

Are formal and functional linguistic mechanisms dissociated in language models?
di: Hanna, Michael, et al.
Pubblicazione: (2025)

Hysteresis Activation Function for Efficient Inference
di: Kimhi, Moshe, et al.
Pubblicazione: (2024)

SAEs Are Good for Steering -- If You Select the Right Features
di: Arad, Dana, et al.
Pubblicazione: (2025)

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs
di: Itzhak, Itay, et al.
Pubblicazione: (2025)

LLM4SFC: Sequential Function Chart Generation via Large Language Models
di: Glick, Ofek, et al.
Pubblicazione: (2025)

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
di: Hanna, Michael, et al.
Pubblicazione: (2024)

ReFACT: Updating Text-to-Image Models by Editing the Text Encoder
di: Arad, Dana, et al.
Pubblicazione: (2023)

Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
di: Tutek, Martin, et al.
Pubblicazione: (2025)

Distinguishing Ignorance from Error in LLM Hallucinations
di: Simhi, Adi, et al.
Pubblicazione: (2024)

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

Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models
di: Kaplan, Guy, et al.
Pubblicazione: (2025)

Silent Tokens, Loud Effects: Padding in LLMs
di: Himelstein, Rom, et al.
Pubblicazione: (2025)

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
di: Katz, Shahar, et al.
Pubblicazione: (2024)

From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs
di: Itzhak, Itay, et al.
Pubblicazione: (2026)

Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer
di: Shao, Shun, et al.
Pubblicazione: (2026)

Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
di: Nikankin, Yaniv, et al.
Pubblicazione: (2024)

Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
di: Nikankin, Yaniv, et al.
Pubblicazione: (2025)

DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models
di: Ventura, Mor, et al.
Pubblicazione: (2025)

Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
di: Wiegreffe, Sarah, et al.
Pubblicazione: (2024)

You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
di: LeVi, Amit, et al.
Pubblicazione: (2025)

Will it Merge? On The Causes of Model Mergeability
di: Rahamim, Adir, et al.
Pubblicazione: (2026)

Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer
di: Simhi, Adi, et al.
Pubblicazione: (2025)

Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
di: Prakash, Nikhil, et al.
Pubblicazione: (2024)

A Dataset for Metaphor Detection in Early Medieval Hebrew Poetry
di: Toker, Michael, et al.
Pubblicazione: (2024)

Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness
di: Ashuach, Tomer, et al.
Pubblicazione: (2026)

Reasoning Models Know What's Important, and Encode It in Their Activations
di: Nikankin, Yaniv, et al.
Pubblicazione: (2026)

Unsupervised Translation of Emergent Communication
di: Levy, Ido, et al.
Pubblicazione: (2025)

CRISP: Persistent Concept Unlearning via Sparse Autoencoders
di: Ashuach, Tomer, et al.
Pubblicazione: (2025)

ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
di: Simhi, Adi, et al.
Pubblicazione: (2025)

Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines
di: Toker, Michael, et al.
Pubblicazione: (2024)

Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
di: Simhi, Adi, et al.
Pubblicazione: (2026)