Copertina

ALTA: Compiler-Based Analysis of Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shaw, Peter, Cohan, James, Eisenstein, Jacob, Lee, Kenton, Berant, Jonathan, Toutanova, Kristina
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
di: Shaw, Peter, et al.
Pubblicazione: (2025)

Effective Reasoning Chains Reduce Intrinsic Dimensionality
di: Prasad, Archiki, et al.
Pubblicazione: (2026)

BgGPT 1.0: Extending English-centric LLMs to other languages
di: Alexandrov, Anton, et al.
Pubblicazione: (2024)

MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games
di: Eisenstein, Jacob, et al.
Pubblicazione: (2026)

Robust Preference Optimization through Reward Model Distillation
di: Fisch, Adam, et al.
Pubblicazione: (2024)

Plantain: Plan-Answer Interleaved Reasoning
di: Liang, Anthony, et al.
Pubblicazione: (2025)

SEMQA: Semi-Extractive Multi-Source Question Answering
di: Schuster, Tal, et al.
Pubblicazione: (2023)

On Evaluating LLM Alignment by Evaluating LLMs as Judges
di: Liu, Yixin, et al.
Pubblicazione: (2025)

Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference
di: Gao, Mingqi, et al.
Pubblicazione: (2024)

Transforming and Combining Rewards for Aligning Large Language Models
di: Wang, Zihao, et al.
Pubblicazione: (2024)

Algorithmic Capabilities of Random Transformers
di: Zhong, Ziqian, et al.
Pubblicazione: (2024)

Observable Propagation: Uncovering Feature Vectors in Transformers
di: Dunefsky, Jacob, et al.
Pubblicazione: (2023)

Calibrating Long-form Generations from Large Language Models
di: Huang, Yukun, et al.
Pubblicazione: (2024)

Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models
di: Belenki, Lior, et al.
Pubblicazione: (2025)

Don't lie to your friends: Learning what you know from collaborative self-play
di: Eisenstein, Jacob, et al.
Pubblicazione: (2025)

References Improve LLM Alignment in Non-Verifiable Domains
di: Shi, Kejian, et al.
Pubblicazione: (2026)

Can Large Language Models Understand Intermediate Representations in Compilers?
di: Jiang, Hailong, et al.
Pubblicazione: (2025)

Latent Context Compilation: Distilling Long Context into Compact Portable Memory
di: Li, Zeju, et al.
Pubblicazione: (2026)

The Anxiety of Influence: Bloom Filters in Transformer Attention Heads
di: Balogh, Peter
Pubblicazione: (2026)

Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers
di: Han, Sungmin, et al.
Pubblicazione: (2025)

Optimizing Diversity and Quality through Base-Aligned Model Collaboration
di: Wang, Yichen, et al.
Pubblicazione: (2025)

Limits of Transformer Language Models on Learning to Compose Algorithms
di: Thomm, Jonathan, et al.
Pubblicazione: (2024)

Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
di: Setlur, Amrith, et al.
Pubblicazione: (2024)

ReIFE: Re-evaluating Instruction-Following Evaluation
di: Liu, Yixin, et al.
Pubblicazione: (2024)

Survey on Evaluation of LLM-based Agents
di: Yehudai, Asaf, et al.
Pubblicazione: (2025)

AIOS Compiler: LLM as Interpreter for Natural Language Programming and Flow Programming of AI Agents
di: Xu, Shuyuan, et al.
Pubblicazione: (2024)

Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization
di: Schnabel, Tobias, et al.
Pubblicazione: (2024)

An Enhanced Dual Transformer Contrastive Network for Multimodal Sentiment Analysis
di: Dao, Phuong Q., et al.
Pubblicazione: (2025)

Power Transformer Fault Prediction Based on Knowledge Graphs
di: Wang, Chao, et al.
Pubblicazione: (2024)

Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs
di: Li, Guchan, et al.
Pubblicazione: (2026)

Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits
di: Ahmad, Areeb, et al.
Pubblicazione: (2025)

Classification of Hope in Textual Data using Transformer-Based Models
di: Ijezue, Chukwuebuka Fortunate, et al.
Pubblicazione: (2025)

Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer
di: Lu, Wenquan, et al.
Pubblicazione: (2025)

Theoretical guarantees on the best-of-n alignment policy
di: Beirami, Ahmad, et al.
Pubblicazione: (2024)

Integrating Locality-Aware Attention with Transformers for General Geometry PDEs
di: Koh, Minsu, et al.
Pubblicazione: (2025)

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
di: Liu, Yixin, et al.
Pubblicazione: (2026)

CAST: Compositional Analysis via Spectral Tracking for Understanding Transformer Layer Functions
di: Fu, Zihao, et al.
Pubblicazione: (2025)

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models
di: Lv, Ang, et al.
Pubblicazione: (2024)

Transformer-Based Multimodal Knowledge Graph Completion with Link-Aware Contexts
di: Ma, Haodi, et al.
Pubblicazione: (2025)

One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs
di: Dunefsky, Jacob, et al.
Pubblicazione: (2025)