Cover Image

Navigating through the hidden embedding space: steering LLMs to improve mental health assessment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ravenda, Federico, Bahrainian, Seyed Ali, Raballo, Andrea, Mira, Antonietta
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Are LLMs effective psychological assessors? Leveraging adaptive RAG for interpretable mental health screening through psychometric practice
by: Ravenda, Federico, et al.
Published: (2025)

The Emotional Spectrum of LLMs: Leveraging Empathy and Emotion-Based Markers for Mental Health Support
by: De Grandi, Alessandro, et al.
Published: (2024)

Diagnosing schizophrenia spectrum disorders: Large language models (LLMs) vs. leading international psychiatrists (LIPs)
by: Andrea Raballo, et al.
Published: (2025)

When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?
by: Zhou, Xinyu, et al.
Published: (2026)

Enhancing Retrieval-Augmented Generation: A Study of Best Practices
by: Li, Siran, et al.
Published: (2025)

A general framework for adaptive nonparametric dimensionality reduction
by: Di Noia, Antonio, et al.
Published: (2025)

Zero-Shot and Efficient Clarification Need Prediction in Conversational Search
by: Lu, Lili, et al.
Published: (2025)

AI-as-exploration: Navigating intelligence space
by: Mollo, Dimitri Coelho
Published: (2024)

ExpertLens: Activation steering features are highly interpretable
by: Fedzechkina, Masha, et al.
Published: (2025)

Exploring and steering the moral compass of Large Language Models
by: Tlaie, Alejandro
Published: (2024)

Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs
by: Ranaldi, Federico, et al.
Published: (2025)

DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs
by: Mousavi, Seyed Mahed, et al.
Published: (2024)

Logit Reweighting for Topic-Focused Summarization
by: Braun, Joschka, et al.
Published: (2025)

Beyond Multiple Choice: Evaluating Steering Vectors for Summarization
by: Braun, Joschka, et al.
Published: (2025)

GenKnowSub: Improving Modularity and Reusability of LLMs through General Knowledge Subtraction
by: Bagherifard, Mohammadtaha, et al.
Published: (2025)

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation
by: Kumarage, Tharindu, et al.
Published: (2025)

Uncovering Hidden Intentions: Exploring Prompt Recovery for Deeper Insights into Generated Texts
by: Give, Louis, et al.
Published: (2024)

Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs
by: Pearman, Edie, et al.
Published: (2026)

A Critical Study of What Code-LLMs (Do Not) Learn
by: Anand, Abhinav, et al.
Published: (2024)

Toward universal steering and monitoring of AI models
by: Beaglehole, Daniel, et al.
Published: (2025)

What's in an embedding? Would a rose by any embedding smell as sweet?
by: Venkatasubramanian, Venkat
Published: (2024)

Can formal argumentative reasoning enhance LLMs performances?
by: Castagna, Federico, et al.
Published: (2024)

Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialogue
by: Alghisi, Simone, et al.
Published: (2024)

Fine-Tuning LLMs for Reliable Medical Question-Answering Services
by: Anaissi, Ali, et al.
Published: (2024)

Can LLMs Capture Human Preferences?
by: Goli, Ali, et al.
Published: (2023)

Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering
by: Chowdhury, Arijit Ghosh, et al.
Published: (2023)

LLMs Are Not Intelligent Thinkers: Introducing Mathematical Topic Tree Benchmark for Comprehensive Evaluation of LLMs
by: Davoodi, Arash Gholami, et al.
Published: (2024)

Evaluating LLMs on Entity Disambiguation in Tables
by: Belotti, Federico, et al.
Published: (2024)

Can sparse autoencoders be used to decompose and interpret steering vectors?
by: Mayne, Harry, et al.
Published: (2024)

Generalist embedding models are better at short-context clinical semantic search than specialized embedding models
by: Excoffier, Jean-Baptiste, et al.
Published: (2024)

Exploiting the English Vocabulary Profile for L2 word-level vocabulary assessment with LLMs
by: Bannò, Stefano, et al.
Published: (2025)

Are complicated loss functions necessary for teaching LLMs to reason?
by: Carrino, Gabriele, et al.
Published: (2026)

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
by: Wang, Haozhe, et al.
Published: (2025)

Contextual Categorization Enhancement through LLMs Latent-Space
by: Bettouche, Zineddine, et al.
Published: (2024)

Digital Socrates: Evaluating LLMs through Explanation Critiques
by: Gu, Yuling, et al.
Published: (2023)

Taking a turn for the better: Conversation redirection throughout the course of mental-health therapy
by: Nguyen, Vivian, et al.
Published: (2024)

Are we describing the same sound? An analysis of word embedding spaces of expressive piano performance
by: Peter, Silvan David, et al.
Published: (2023)

Fine-Tuning LLMs for Low-Resource Dialect Translation: The Case of Lebanese
by: Yakhni, Silvana, et al.
Published: (2025)

Rethinking the Understanding Ability across LLMs through Mutual Information
by: Wang, Shaojie, et al.
Published: (2025)

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
by: Raimondi, Bianca, et al.
Published: (2025)