RISE is an inference-time semantic reranking framework that refines low-confidence predictions in rhetorical role labeling using contrastively learned label representations, delivering an average +9.15 macro-F1 gain on hard examples across eight datasets and seven models.
QLoRA: Efficient Finetuning of Quantized LLMs , url =
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
LLMs prompted with few-shot examples and rationales generate better reasoned distractors for MCQs than fine-tuned contrastive models across six benchmarks.
torchtune is a modular PyTorch library for LLM post-training that delivers competitive performance and memory efficiency while supporting rapid research iteration through hackable components.
Two-stage multilingual then dataset-specific adapter fine-tuning of Gemma-3-27b with headword XML mention representation and iterative annotation achieved first place in the CRAC 2026 LLM track.
A literature survey synthesizing benchmarks, architectures, training strategies, and evaluation methods for mathematical reasoning in LLMs, based on roughly 120 papers.
citing papers explorer
-
Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling
RISE is an inference-time semantic reranking framework that refines low-confidence predictions in rhetorical role labeling using contrastively learned label representations, delivering an average +9.15 macro-F1 gain on hard examples across eight datasets and seven models.
-
Beyond Fine-Tuning: In-Context Learning and Chain-of-Thought for Reasoned Distractor Generation
LLMs prompted with few-shot examples and rationales generate better reasoned distractors for MCQs than fine-tuned contrastive models across six benchmarks.
-
torchtune: PyTorch native post-training library
torchtune is a modular PyTorch library for LLM post-training that delivers competitive performance and memory efficiency while supporting rapid research iteration through hackable components.
-
Closing the Gap at CRAC 2026: Two-Stage Adaptation for LLM-Based Multilingual Coreference Resolution
Two-stage multilingual then dataset-specific adapter fine-tuning of Gemma-3-27b with headword XML mention representation and iterative annotation achieved first place in the CRAC 2026 LLM track.
-
Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges
A literature survey synthesizing benchmarks, architectures, training strategies, and evaluation methods for mathematical reasoning in LLMs, based on roughly 120 papers.