Copertina

Circuit Stability Characterizes Language Model Generalization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Sun, Alan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Algorithmic Phase Transitions in Language Models: A Mechanistic Case Study of Arithmetic
di: Sun, Alan, et al.
Pubblicazione: (2024)

Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability
di: Chang, Tyler A., et al.
Pubblicazione: (2023)

How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits
di: Li, Michael, et al.
Pubblicazione: (2026)

On Characterizations for Language Generation: Interplay of Hallucinations, Breadth, and Stability
di: Kalavasis, Alkis, et al.
Pubblicazione: (2024)

Understanding Language Model Circuits through Knowledge Editing
di: Ge, Huaizhi, et al.
Pubblicazione: (2024)

Architecture, Not Scale: Circuit Localization in Large Language Models
di: Venkatesh, Sohan
Pubblicazione: (2026)

Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension
di: Yin, Fan, et al.
Pubblicazione: (2024)

Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
di: Luo, Xiaoyu, et al.
Pubblicazione: (2026)

Mechanistic Circuit-Based Knowledge Editing in Large Language Models
di: Zhao, Tianyi, et al.
Pubblicazione: (2026)

CircuitSynth: Reliable Synthetic Data Generation
di: Cheng, Zehua, et al.
Pubblicazione: (2026)

Electronic Circuit Principles of Large Language Models
di: Chen, Qiguang, et al.
Pubblicazione: (2025)

CktFormalizer: Autoformalization of Natural Language into Circuit Representations
di: Xiong, Jing, et al.
Pubblicazione: (2026)

Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models
di: Lasnier, Théo, et al.
Pubblicazione: (2026)

Applying Large Language Models to Characterize Public Narratives
di: Poole-Dayan, Elinor, et al.
Pubblicazione: (2025)

Characterizing the Expressivity of Fixed-Precision Transformer Language Models
di: Li, Jiaoda, et al.
Pubblicazione: (2025)

Characterizing the Role of Similarity in the Property Inferences of Language Models
di: Rodriguez, Juan Diego, et al.
Pubblicazione: (2024)

Circuit Component Reuse Across Tasks in Transformer Language Models
di: Merullo, Jack, et al.
Pubblicazione: (2023)

Characterizing Selective Refusal Bias in Large Language Models
di: Khorramrouz, Adel, et al.
Pubblicazione: (2025)

Representational and Behavioral Stability of Truth in Large Language Models
di: Dies, Samantha, et al.
Pubblicazione: (2025)

Lemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training Data
di: Toporkov, Olia, et al.
Pubblicazione: (2025)

FakeGPT: Fake News Generation, Explanation and Detection of Large Language Models
di: Huang, Yue, et al.
Pubblicazione: (2023)

Boosting Disfluency Detection with Large Language Model as Disfluency Generator
di: Cheng, Zhenrong, et al.
Pubblicazione: (2024)

Detecting and Characterizing Planning in Language Models
di: Nainani, Jatin, et al.
Pubblicazione: (2025)

Evaluating the Generation Capabilities of Large Chinese Language Models
di: Zeng, Hui, et al.
Pubblicazione: (2023)

NEO-BENCH: Evaluating Robustness of Large Language Models with Neologisms
di: Zheng, Jonathan, et al.
Pubblicazione: (2024)

Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigation
di: Li, Bo, et al.
Pubblicazione: (2025)

Discursive Circuits: How Do Language Models Understand Discourse Relations?
di: Miao, Yisong, et al.
Pubblicazione: (2025)

AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO
di: Dao, Alan, et al.
Pubblicazione: (2025)

Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
di: Mondorf, Philipp, et al.
Pubblicazione: (2024)

Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models
di: O'Neill, Charles, et al.
Pubblicazione: (2024)

The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
di: Lu, Christina, et al.
Pubblicazione: (2026)

Prompt Stability Scoring for Text Annotation with Large Language Models
di: Barrie, Christopher, et al.
Pubblicazione: (2024)

Tending Towards Stability: Convergence Challenges in Small Language Models
di: Martinez, Richard Diehl, et al.
Pubblicazione: (2024)

BabyHGRN: Exploring RNNs for Sample-Efficient Training of Language Models
di: Haller, Patrick, et al.
Pubblicazione: (2024)

Effective Large Language Model Adaptation for Improved Grounding and Citation Generation
di: Ye, Xi, et al.
Pubblicazione: (2023)

Language Model Circuits Are Sparse in the Neuron Basis
di: Arora, Aryaman, et al.
Pubblicazione: (2026)

Dissecting the Ledger: Locating and Suppressing "Liar Circuits" in Financial Large Language Models
di: Mirajkar, Soham
Pubblicazione: (2025)

Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding
di: Qu, Fanyi, et al.
Pubblicazione: (2024)

Algorithmic Stability in Infinite Dimensions: Characterizing Unconditional Convergence in Banach Spaces
di: Spyra, Przemysław
Pubblicazione: (2026)

BEAR: A Unified Framework for Evaluating Relational Knowledge in Causal and Masked Language Models
di: Wiland, Jacek, et al.
Pubblicazione: (2024)