paper-with-me

Papers

Internalized Self-Correction for Large Language Models

2024-12-21 · Nishanth Upadhyaya, Raghavendra Sridharamurthy

In this article, we introduce 'Internalized Self-Correction' (InSeC) for large language models (LLMs). While many approaches exist for self-reflection at inference time, we propose a novel method that combines ideas from negative sampling, self-reflection during training, and inference time. InSeC allows LLMs to correct themselves by introducing mistakes and their corresponding corrections during training, thereby converting the learning process into a true supervised learning task with both positive and negative examples. This approach can be extended to improve instruction following and correct hallucinations or incorrect sentences generated by LLMs.

📄 PDF Abstract BibTeX arXiv:2412.16653

Code (0)

등록된 구현이 없습니다.

Tasks

Instruction Following

Similar Papers 제목 키워드 기반

PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft

2026-05-26 · Yuchen Guo, Junli Gong, Weicheng Wang, Hongmin Cai 외 arxiv

We present PEAM, a Parametric Embodied Agent Memory framework in Minecraft that transforms agent memory from inference-time retrieval into parameter-resident skills internalized through experience. PEAM pairs a slow deli…

Continual Learning

On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance

2026-05-30 · Etienne Casanova, Rafal Kocielnik, R. Michael Alvarez arxiv

Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-internalized priors interact with user-provided instructions. We investigate…

TInR: Exploring Tool-Internalized Reasoning in Large Language Models

2026-04-12 · Qiancheng Xu, Yongqi Li, Fan Liu, Hongru Wang 외 arxiv

Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools during reasoning. Existing TIR methods typically rely on external tool docu…

Reinforcement Learning

HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models

2026-08-13 · Jiazi Bu, Pengyang Ling, Yujie Zhou, Yibin Wang 외 arxiv

Text-Image-to-Video (TI2V) models are an emerging unified architecture, where a single model simultaneously supports text-to-video (T2V) and image-to-video (I2V) generation. Given a high-quality first frame or a detailed…

Self-Improving Large Language Models via Progressive Experience Evolution

2026-08-03 · Shijie Ren, Xiting Wang, Meng Li, Yujie Guo 외 arxiv

Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transforming transient interaction experience into persistent model capabilitie…

Mathematical ReasoningReinforcement Learning