Image de couverture de livre

ContraSim -- Analyzing Neural Representations Based on Contrastive Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Rahamim, Adir, Belinkov, Yonatan
Format:	Preprint
Publié:	2023
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Fast Forwarding Low-Rank Training
par: Rahamim, Adir, et autres
Publié: (2024)

Will it Merge? On The Causes of Model Mergeability
par: Rahamim, Adir, et autres
Publié: (2026)

Growing a Tail: Increasing Output Diversity in Large Language Models
par: Shur-Ofry, Michal, et autres
Publié: (2024)

Contrastive Similarity Learning for Market Forecasting: The ContraSim Framework
par: Vinden, Nicholas, et autres
Publié: (2025)

Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
par: Iskander, Shadi, et autres
Publié: (2024)

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
par: Yu, Zeping, et autres
Publié: (2025)

Concept-Best-Matching: Evaluating Compositionality in Emergent Communication
par: Carmeli, Boaz, et autres
Publié: (2024)

Are formal and functional linguistic mechanisms dissociated in language models?
par: Hanna, Michael, et autres
Publié: (2025)

REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space
par: Ashuach, Tomer, et autres
Publié: (2024)

Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods
par: Blau, Tsachi, et autres
Publié: (2024)

SAEs Are Good for Steering -- If You Select the Right Features
par: Arad, Dana, et autres
Publié: (2025)

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs
par: Itzhak, Itay, et autres
Publié: (2025)

DEPTH: Discourse Education through Pre-Training Hierarchically
par: Bamberger, Zachary, et autres
Publié: (2024)

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
par: Hanna, Michael, et autres
Publié: (2024)

ReFACT: Updating Text-to-Image Models by Editing the Text Encoder
par: Arad, Dana, et autres
Publié: (2023)

Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
par: Tutek, Martin, et autres
Publié: (2025)

Distinguishing Ignorance from Error in LLM Hallucinations
par: Simhi, Adi, et autres
Publié: (2024)

Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs
par: Simhi, Adi, et autres
Publié: (2024)

Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models
par: Kaplan, Guy, et autres
Publié: (2025)

Silent Tokens, Loud Effects: Padding in LLMs
par: Himelstein, Rom, et autres
Publié: (2025)

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
par: Katz, Shahar, et autres
Publié: (2024)

From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs
par: Itzhak, Itay, et autres
Publié: (2026)

Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer
par: Shao, Shun, et autres
Publié: (2026)

Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
par: Nikankin, Yaniv, et autres
Publié: (2024)

Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
par: Nikankin, Yaniv, et autres
Publié: (2025)

DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models
par: Ventura, Mor, et autres
Publié: (2025)

Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
par: Wiegreffe, Sarah, et autres
Publié: (2024)

Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer
par: Simhi, Adi, et autres
Publié: (2025)

Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
par: Prakash, Nikhil, et autres
Publié: (2024)

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
par: Orgad, Hadas, et autres
Publié: (2024)

A Dataset for Metaphor Detection in Early Medieval Hebrew Poetry
par: Toker, Michael, et autres
Publié: (2024)

Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness
par: Ashuach, Tomer, et autres
Publié: (2026)

Reasoning Models Know What's Important, and Encode It in Their Activations
par: Nikankin, Yaniv, et autres
Publié: (2026)

Unsupervised Translation of Emergent Communication
par: Levy, Ido, et autres
Publié: (2025)

CRISP: Persistent Concept Unlearning via Sparse Autoencoders
par: Ashuach, Tomer, et autres
Publié: (2025)

ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
par: Simhi, Adi, et autres
Publié: (2025)

Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines
par: Toker, Michael, et autres
Publié: (2024)

Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
par: Simhi, Adi, et autres
Publié: (2026)

Position-aware Automatic Circuit Discovery
par: Haklay, Tal, et autres
Publié: (2025)

Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models
par: Toker, Michael, et autres
Publié: (2025)