Imagen de Portada

Towards Interpretable Soft Prompts

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Patel, Oam, Wang, Jason, Nayak, Nikhil Shivakumar, Srinivas, Suraj, Lakkaraju, Himabindu
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computation and Language 68T50 I.2.0; G.3
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning
por: Nayak, Nikhil Shivakumar, et al.
Publicado: (2025)

March Madness Tournament Predictions Model: A Mathematical Modeling Approach
por: McIver, Christian, et al.
Publicado: (2025)

Graph Attention for Heterogeneous Graphs with Positional Encoding
por: Nayak, Nikhil Shivakumar
Publicado: (2025)

Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Question
por: Rosales, Rafael, et al.
Publicado: (2025)

Prompt Tuned Embedding Classification for Multi-Label Industry Sector Allocation
por: Buchner, Valentin Leonhard, et al.
Publicado: (2023)

Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?
por: Wang, Yongjie, et al.
Publicado: (2025)

Large Language Models Report Subjective Experience Under Self-Referential Processing
por: Berg, Cameron, et al.
Publicado: (2025)

Chatbots put to the test in math and logic problems: A preliminary comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard
por: Plevris, Vagelis, et al.
Publicado: (2023)

Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA
por: Badshah, Sher, et al.
Publicado: (2024)

GIM: Evaluating models via tasks that integrate multiple cognitive domains
por: Patel, Rohit, et al.
Publicado: (2026)

Mathematical Modeling of Option Pricing with an Extended Black-Scholes Framework
por: Nayak, Nikhil Shivakumar
Publicado: (2025)

Hopscotch: Discovering and Skipping Redundancies in Language Models
por: Eyceoz, Mustafa, et al.
Publicado: (2025)

Proceedings of the 20th International Conference on Knowledge, Information and Creativity Support Systems (KICSS 2025)
por: Hayama, Edited by Tessai, et al.
Publicado: (2025)

Data and AI governance: Promoting equity, ethics, and fairness in large language models
por: Abhishek, Alok, et al.
Publicado: (2025)

SHARP: Social Harm Analysis via Risk Profiles for Measuring Inequities in Large Language Models
por: Abhishek, Alok, et al.
Publicado: (2026)

BEATS: Bias Evaluation and Assessment Test Suite for Large Language Models
por: Abhishek, Alok, et al.
Publicado: (2025)

Reasoning Promotes Robustness in Theory of Mind Tasks
por: de Haan, Ian B., et al.
Publicado: (2026)

Correcting Stochastic Update Bias in Preconditioned Language Model Optimizers
por: Nayak, Nikhil, et al.
Publicado: (2026)

CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering
por: Badshah, Sher, et al.
Publicado: (2025)

Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure
por: Sarkar, Nilesh, et al.
Publicado: (2026)

Multi-Model Synthetic Training for Mission-Critical Small Language Models
por: Platt, Nolan, et al.
Publicado: (2025)

JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vector Manipulation
por: Huang, Yingbing, et al.
Publicado: (2025)

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models
por: Guo, Dongxin, et al.
Publicado: (2026)

Mubeen AI: A Specialized Arabic Language Model for Heritage Preservation and User Intent Understanding
por: Aljafari, Mohammed, et al.
Publicado: (2025)

Enhancing Feature Selection and Interpretability in AI Regression Tasks Through Feature Attribution
por: Hinterleitner, Alexander, et al.
Publicado: (2024)

Position: Mechanistic Interpretability Must Disclose Identification Assumptions for Causal Claims
por: Lin, Zezheng, et al.
Publicado: (2026)

Interpretability Can Be Actionable
por: Orgad, Hadas, et al.
Publicado: (2026)

AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science
por: Luo, An, et al.
Publicado: (2025)

Vibe-Creation: The Epistemology of Human-AI Emergent Cognition
por: Levin, Ilya
Publicado: (2026)

Improving Time Series Classification with Representation Soft Label Smoothing
por: Ma, Hengyi, et al.
Publicado: (2024)

Stealth edits to large language models
por: Sutton, Oliver J., et al.
Publicado: (2024)

5G Traffic Prediction with Time Series Analysis
por: Nayak, Nikhil, et al.
Publicado: (2021)

Learning What Matters: Probabilistic Task Selection via Mutual Information for Model Finetuning
por: Chanda, Prateek, et al.
Publicado: (2025)

MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional
por: Cruz, Roberto, et al.
Publicado: (2026)

When Your Own Output Becomes Your Training Data: Noise-to-Meaning Loops and a Formal RSI Trigger
por: Ando, Rintaro
Publicado: (2025)

A Mixed User-Centered Approach to Enable Augmented Intelligence in Intelligent Tutoring Systems: The Case of MathAIde app
por: Guerino, Guilherme, et al.
Publicado: (2025)

Prompt-Efficient Fine-Tuning for GPT-like Deep Models to Reduce Hallucination and to Improve Reproducibility in Scientific Text Generation Using Stochastic Optimisation Techniques
por: Sulimov, Daniil
Publicado: (2024)

Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification
por: Arends, Bauke, et al.
Publicado: (2024)

Filtered not Mixed: Stochastic Filtering-Based Online Gating for Mixture of Large Language Models
por: Saqur, Raeid, et al.
Publicado: (2024)

MATRIX: Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation
por: Lim, Ernest, et al.
Publicado: (2025)