Image de couverture de livre

Improving Causal Interventions in Amnesic Probing with Mean Projection or LEACE

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dobrzeniecka, Alicja, Fokkens, Antske, Sommerauer, Pia
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies
par: Kamp, Jonathan, et autres
Publié: (2025)

The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement
par: Kamp, Jonathan, et autres
Publié: (2024)

Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs
par: Troshin, Sergey, et autres
Publié: (2025)

Annotation-Efficient Vision-Language Model Adaptation to the Polish Language Using the LLaVA Framework
par: Statkiewicz, Grzegorz, et autres
Publié: (2026)

Investigating the Robustness of Modelling Decisions for Few-Shot Cross-Topic Stance Detection: A Preregistered Study
par: Reuver, Myrthe, et autres
Publié: (2024)

DefVerify: Do Hate Speech Models Reflect Their Dataset's Definition?
par: Khurana, Urja, et autres
Publié: (2024)

On the Low-Rank Parametrization of Reward Models for Controlled Language Generation
par: Troshin, Sergey, et autres
Publié: (2024)

How Reliable are Causal Probing Interventions?
par: Canby, Marc, et autres
Publié: (2024)

Balancing the Scales: Reinforcement Learning for Fair Classification
par: Eshuijs, Leon, et autres
Publié: (2024)

Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification
par: Eshuijs, Leon, et autres
Publié: (2025)

Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data
par: Jin, Charles, et autres
Publié: (2024)

Asking a Language Model for Diverse Responses
par: Troshin, Sergey, et autres
Publié: (2025)

Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?
par: Khurana, Urja, et autres
Publié: (2024)

Beyond Classification: Dynamic Adapter Routing for Continual Multimodal Retrieval
par: Dobrzeniecka, Alicja, et autres
Publié: (2026)

CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification
par: Wang, Yian, et autres
Publié: (2026)

Probing Causality Manipulation of Large Language Models
par: Zhang, Chenyang, et autres
Publié: (2024)

Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to Semantics
par: Lee, Isabelle, et autres
Publié: (2024)

Estimating Causal Effects of Text Interventions Leveraging LLMs
par: Guo, Siyi, et autres
Publié: (2024)

Nuance Matters: Probing Epistemic Consistency in Causal Reasoning
par: Cui, Shaobo, et autres
Publié: (2024)

Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents
par: Srivastava, Saksham Sahai
Publié: (2026)

Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
par: Roy, Amartya, et autres
Publié: (2026)

Debiasing Reward Models via Causally Motivated Inference-Time Intervention
par: Shinoda, Kazutoshi, et autres
Publié: (2026)

Information Gain-Guided Causal Intervention for Autonomous Debiasing Large Language Models
par: Sun, Zhouhao, et autres
Publié: (2025)

Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions
par: Boguraev, Sasha, et autres
Publié: (2025)

From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency
par: Ohmer, Xenia, et autres
Publié: (2024)

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
par: Yang, Zhen, et autres
Publié: (2025)

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
par: Kang, Diancheng, et autres
Publié: (2026)

Structured Thinking Matters: Improving LLMs Generalization in Causal Inference Tasks
par: Sun, Wentao, et autres
Publié: (2025)

A Causal Language Modeling Detour Improves Encoder Continued Pretraining
par: Touchent, Rian, et autres
Publié: (2026)

Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction
par: Puyin, Li, et autres
Publié: (2026)

Enhancing Complex Causality Extraction via Improved Subtask Interaction and Knowledge Fusion
par: Gao, Jinglong, et autres
Publié: (2024)

Do BERT Embeddings Encode Narrative Dimensions? A Token-Level Probing Analysis of Time, Space, Causality, and Character in Fiction
par: Bei, Beicheng, et autres
Publié: (2026)

Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token
par: Lin, Ailiang, et autres
Publié: (2025)

Knowledge Graph Structure as Prompt: Improving Small Language Models Capabilities for Knowledge-based Causal Discovery
par: Susanti, Yuni, et autres
Publié: (2024)

Simulating Identity, Propagating Bias: Abstraction and Stereotypes in LLM-Generated Text
par: Sommerauer, Pia, et autres
Publié: (2025)

Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP
par: Khurana, Urja, et autres
Publié: (2026)

LEACE: Perfect linear concept erasure in closed form
par: Belrose, Nora, et autres
Publié: (2023)

CausalEval: Towards Better Causal Reasoning in Language Models
par: Yu, Longxuan, et autres
Publié: (2024)

Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference
par: Vashishtha, Aniket, et autres
Publié: (2023)

Simple Projection Variants Improve ColBERT Performance
par: Clavié, Benjamin, et autres
Publié: (2025)