Cover Image

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Stanley, Bulusu, Vaidehi, Yasunaga, Oscar, Lau, Clayton, Blondin, Cole, O'Brien, Sean, Zhu, Kevin, Sharma, Vasu
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Causal Language Control in Multilingual Transformers via Sparse Feature Steering
by: Chou, Cheng-Ting, et al.
Published: (2025)

Universal Neurons in GPT-2: Emergence, Persistence, and Functional Impact
by: Nandan, Advey, et al.
Published: (2025)

Interpreting the Latent Structure of Operator Precedence in Language Models
by: Yugeswardeenoo, Dharunish, et al.
Published: (2025)

Semantic Convergence: Investigating Shared Representations Across Scaled LLMs
by: Son, Daniel, et al.
Published: (2025)

Rosetta-PL: Propositional Logic as a Benchmark for Large Language Model Reasoning
by: Baek, Shaun, et al.
Published: (2025)

NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts
by: Gupta, Abhay, et al.
Published: (2025)

The Geometry of Harmfulness in LLMs through Subconcept Probing
by: Shah, McNair, et al.
Published: (2025)

Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning
by: Lu, Leo, et al.
Published: (2025)

SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning
by: Aluru, Aayush, et al.
Published: (2025)

Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques
by: Xiong, Lang, et al.
Published: (2025)

Pause-Tuning for Long-Context Comprehension: A Lightweight Approach to LLM Attention Recalibration
by: Begin, James, et al.
Published: (2025)

Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT
by: Do, Timothy, et al.
Published: (2025)

ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models
by: Khalid, Haziq Mohammad, et al.
Published: (2025)

Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation
by: Le, Duy, et al.
Published: (2025)

Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation
by: Csizmadia, Daniel, et al.
Published: (2025)

WOLF: Werewolf-based Observations for LLM Deception and Falsehoods
by: Agarwal, Mrinal, et al.
Published: (2025)

TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models
by: Liu, Joshua, et al.
Published: (2025)

Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks
by: Yugeswardeenoo, Dharunish, et al.
Published: (2024)

Deconstructing Bias: A Multifaceted Framework for Diagnosing Cultural and Compositional Inequities in Text-to-Image Generative Models
by: Said, Muna Numan, et al.
Published: (2025)

COREVQA: A Crowd Observation and Reasoning Entailment Visual Question Answering Benchmark
by: Chintapatla, Ishant, et al.
Published: (2025)

Advancing Uto-Aztecan Language Technologies: A Case Study on the Endangered Comanche Language
by: C, Jesus Alvarez, et al.
Published: (2025)

From Bias to Balance: Detecting Facial Expression Recognition Biases in Large Multimodal Foundation Models
by: Chhua, Kaylee, et al.
Published: (2024)

Error Reflection Prompting: Can Large Language Models Successfully Understand Errors?
by: Li, Jason, et al.
Published: (2025)

CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning
by: Rufail, Andrew, et al.
Published: (2025)

Systemization of Knowledge: Resilience and Fault Tolerance in Cyber-Physical Systems
by: Bulusu, Rahul
Published: (2025)

MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered
by: Mirza, Imran, et al.
Published: (2025)

Approaching the Source of Symbol Grounding with Confluent Reductions of Abstract Meaning Representation Directed Graphs
by: Goulet, Nicolas, et al.
Published: (2025)

The Arm Qubit: A Superconducting Qubit Co-Designed for Coherence and Coupling
by: Kline, Jeremy B., et al.
Published: (2025)

Direct Confidence Alignment: Aligning Verbalized Confidence with Internal Confidence In Large Language Models
by: Zhang, Glenn, et al.
Published: (2025)

Using a Capability Approach to Explore How People With Intellectual Disabilities Can Lead Flourishing Lives
by: Sara Ryan, et al.
Published: (2024)

Exploring GPT-4 for Robotic Agent Strategy with Real-Time State Feedback and a Reactive Behaviour Framework
by: O'Brien, Thomas, et al.
Published: (2025)

AAVENUE: Detecting LLM Biases on NLU Tasks in AAVE via a Novel Benchmark
by: Gupta, Abhay, et al.
Published: (2024)

Ultrafast Superconducting Qubit Readout with the Quarton Coupler
by: Ye, Yufeng, et al.
Published: (2024)

Exploring Virtual Reality as a Tool for Enhancing Teaching and Learning Anatomy to Medical Students: A Feasibility and Acceptability Study
by: Aifric Walsh, et al.
Published: (2025)

SonamicExamples
by: O'Brien, Harry
Published: (2026)

Contrasting nonstructural carbohydrate dynamics of tropical tree seedlings under water deficit and variability
by: O'Brien, Michael
Published: (2026)

Geant4 Simulated Dataset for the Relativistic Electron and Proton Telescope integrated little experiment-3
by: O'Brien, Declan
Published: (2025)

Developing Pre-Supernova Neutrino Model Support for sntools
by: O'Brien, Ellie
Published: (2026)

Traversing European Coastlines (TREC) particle count and meterological data from land (2023-2024)
by: O'Brien, James
Published: (2026)

Transactions with the World
by: O’Brien, Adam
Published: (2020)