Knowledge Tree
International Conference on Learning Representations
Also known as: The Thirteenth International Conference on Learning Representations, The Eleventh International Conference on Learning Representations
Facts (14)
Sources
A Survey on the Theory and Mechanism of Large Language Models arxiv.org Mar 12, 2026 11 facts
referenceThe paper 'Training on the test task confounds evaluation and emergence' was published in The Thirteenth International Conference on Learning Representations.
referenceThe paper 'MACPO: weak-to-strong alignment via multi-agent contrastive preference optimization' is cited in section 7.2.2 of 'A Survey on the Theory and Mechanism of Large Language Models' and was presented at The Thirteenth International Conference on Learning Representations.
referenceThe paper 'Learning dynamics of LLM finetuning' was presented at The Thirteenth International Conference on Learning Representations and is cited in section 3.2.3 of 'A Survey on the Theory and Mechanism of Large Language Models'.
referenceThe paper 'Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data' was published in The Thirteenth International Conference on Learning Representations.
referenceThe paper 'Unintentional unalignment: likelihood displacement in direct preference optimization' was presented at The Thirteenth International Conference on Learning Representations and is cited in section 3.2.3 of 'A Survey on the Theory and Mechanism of Large Language Models'.
referenceThe paper 'Iterative label refinement matters more than preference optimization under weak supervision' was presented at The Thirteenth International Conference on Learning Representations (ICLR).
referenceThe paper 'Weak-to-strong generalization through the data-centric lens' was published in The Thirteenth International Conference on Learning Representations and is cited in 'A Survey on the Theory and Mechanism of Large Language Models'.
referenceThe paper 'Understanding factual recall in transformers via associative memories' was presented at The Thirteenth International Conference on Learning Representations.
referenceThe paper 'Provable weak-to-strong generalization via benign overfitting' was presented at The Thirteenth International Conference on Learning Representations.
referenceThe paper 'U-shaped and inverted-u scaling behind emergent abilities of large language models' was presented at The Thirteenth International Conference on Learning Representations.
referenceThe paper 'High-dimensional analysis of knowledge distillation: weak-to-strong generalization and scaling laws' was published in The Thirteenth International Conference on Learning Representations.
Building Trustworthy NeuroSymbolic AI Systems - arXiv arxiv.org 1 fact
referenceKwon et al. (2022) published 'Reward Design with Language Models' in The Eleventh International Conference on Learning Representations.
Re-evaluating Hallucination Detection in LLMs - arXiv arxiv.org Aug 13, 2025 1 fact
referenceJie Ren et al. (2023) proposed methods for out-of-distribution detection and selective generation for conditional language models in their paper presented at The Eleventh International Conference on Learning Representations.
The Synergy of Symbolic and Connectionist AI in LLM-Empowered ... arxiv.org Jul 11, 2024 1 fact
referenceThomas N. Kipf and Max Welling introduced semi-supervised classification using graph convolutional networks at the International Conference on Learning Representations in 2022.