Imagen de Portada

LLMs can learn self-restraint through iterative self-reflection

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Piché, Alexandre, Milios, Aristides, Bahdanau, Dzmitry, Pal, Chris
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Forecasting Downstream Performance of LLMs With Proxy Metrics
por: Patel, Arkil, et al.
Publicado: (2026)

PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation
por: Piché, Alexandre, et al.
Publicado: (2025)

BRIDGE: Predicting Human Task Completion Time From Model Performance
por: Liu, Fengyuan, et al.
Publicado: (2026)

ROSA: Random Subspace Adaptation for Efficient Fine-Tuning
por: Hameed, Marawan Gamal Abdel, et al.
Publicado: (2024)

How to Get Your LLM to Generate Challenging Problems for Evaluation
por: Patel, Arkil, et al.
Publicado: (2025)

Evaluating In-Context Learning of Libraries for Code Generation
por: Patel, Arkil, et al.
Publicado: (2023)

Probing self-attention in self-supervised speech models for cross-linguistic differences
por: Gopinath, Sai, et al.
Publicado: (2024)

NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild
por: Murty, Shikhar, et al.
Publicado: (2024)

Cropping outperforms dropout as an augmentation strategy for self-supervised training of text embeddings
por: González-Márquez, Rita, et al.
Publicado: (2025)

Exploring Precision and Recall to assess the quality and diversity of LLMs
por: Bronnec, Florian Le, et al.
Publicado: (2024)

Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
por: Dang, Quy-Anh, et al.
Publicado: (2025)

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

A low latency attention module for streaming self-supervised speech representation learning
por: Ma, Jianbo, et al.
Publicado: (2023)

Sensitivity of Generative VLMs to Semantically and Lexically Altered Prompts
por: Dumpala, Sri Harsha, et al.
Publicado: (2024)

Are self-explanations from Large Language Models faithful?
por: Madsen, Andreas, et al.
Publicado: (2024)

Understanding Knowledge Drift in LLMs through Misinformation
por: Fastowski, Alina, et al.
Publicado: (2024)

Small sample-based adaptive text classification through iterative and contrastive description refinement
por: Rajeev, Amrit, et al.
Publicado: (2025)

From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation
por: Malik, Ali, et al.
Publicado: (2024)

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines
por: Jørgensen, Mikkel Godsk, et al.
Publicado: (2026)

Improving Self Consistency in LLMs through Probabilistic Tokenization
por: Sathe, Ashutosh, et al.
Publicado: (2024)

How well can off-the-shelf LLMs elucidate molecular structures from mass spectra using chain-of-thought reasoning?
por: Wang, Yufeng, et al.
Publicado: (2026)

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

Density estimation with LLMs: a geometric investigation of in-context learning trajectories
por: Liu, Toni J. B., et al.
Publicado: (2024)

Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards
por: Lara, Luis, et al.
Publicado: (2026)

Cartridges: Lightweight and general-purpose long context representations via self-study
por: Eyuboglu, Sabri, et al.
Publicado: (2025)

SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts
por: Muzio, Alexandre, et al.
Publicado: (2024)

Frontier AI systems have surpassed the self-replicating red line
por: Pan, Xudong, et al.
Publicado: (2024)

A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs
por: Goel, Raghavv, et al.
Publicado: (2026)

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
por: Xiong, Zheyang, et al.
Publicado: (2024)

LLMs cannot find reasoning errors, but can correct them given the error location
por: Tyen, Gladys, et al.
Publicado: (2023)

SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
por: Song, Jiwon, et al.
Publicado: (2024)

Predicting the Performance of Black-box LLMs through Follow-up Queries
por: Sam, Dylan, et al.
Publicado: (2025)

Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs
por: Sheshanarayana, Disha, et al.
Publicado: (2026)

Two are better than one: Context window extension with multi-grained self-injection
por: Han, Wei, et al.
Publicado: (2024)

IAM: Efficient Inference through Attention Mapping between Different-scale LLMs
por: Zhao, Yi, et al.
Publicado: (2025)

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
por: Treutlein, Johannes, et al.
Publicado: (2024)

LLMs can see and hear without any training
por: Ashutosh, Kumar, et al.
Publicado: (2025)

Exploring validation metrics for offline model-based optimisation with diffusion models
por: Beckham, Christopher, et al.
Publicado: (2022)

Building Multilingual Datasets for Predicting Mental Health Severity through LLMs: Prospects and Challenges
por: Skianis, Konstantinos, et al.
Publicado: (2024)

Mitigating Semantic Drift: Evaluating LLMs' Efficacy in Psychotherapy through MI Dialogue Summarization
por: Kumar, Vivek, et al.
Publicado: (2025)