internal representation

A Shared Geometry of Difficulty in Multilingual Language Models ACL 2026 HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token EACL 2026 LLM Safety From Within: Detecting Harmful Content with Internal Representations ACL 2026 Mary, the Cheeseburger-Eating Vegetarian: Do LLMs Recognize Incoherence in Narratives? EACL 2026 Polarity-Aware Probing for Quantifying Latent Alignment in Language Models AAAI 2026 Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning ACL 2026 Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations ACL 2026 Analyzing LLMs’ Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations ACL 2025 Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressions EMNLP 2025 Calibrating LLM Confidence by Probing Perturbed Representation Stability EMNLP 2025 Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models Interspeech 2025 Derivational Probing: Unveiling the Layer-wise Derivation of Syntactic Structures in Neural Language Models CoNLL 2025 Detecting Hallucination in Large Language Models Through Deep Internal Representation Analysis IJCAI 2025 Do LLMs ``know'' internally when they follow instructions? ICLR 2025 Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks’ Internal Representations ICML 2025 Exploiting Contextual Knowledge in LLMs through 𝒱-usable Information based Layer Enhancement ACL 2025 HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead NAACL 2025 How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders EMNLP 2025 Jailbreak Defense in LLM via Attention Head Analysis and Selective Intervention ACML 2025 Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages AAAI 2025 Learning from Hallucinations: Mitigating Hallucinations in LLMs via Internal Representation Intervention IJCNLP 2025 LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations ICLR 2025 Mechanistic Interpretability for Steering Vision-Language-Action Models CoRL 2025 Memorization ≠ Understanding: Do Large Language Models Have the Ability of Scenario Cognition? EMNLP 2025 Probing for Arithmetic Errors in Language Models EMNLP 2025