Self-distillation reduces fine-tuning-induced hallucinations, lowering factual forgetting from 15% to 3%.

Guy Kaplan, Zorik Gekhman, Zhen Zhu et al.

SpecGuard enhances multi-step reasoning efficiency and accuracy using internal signals for step-level verification.

Kiran Purohit, Ramasuri Narayanam, Soumyabrata Pal

MADE benchmark enhances multi-label text classification accuracy with uncertainty quantification, especially in medical device adverse events.

Raunak Agarwal, Markus Wenzel, Simon Baur et al.

LLMs generate excessive content in translations; detection strategies improve translation quality.

Lisa Vasileva, Karin Sim

Study finds RAG system improvements in retrieval do not guarantee better QA performance in AI policy analysis.

Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur et al.

MARCH framework significantly reduces LLM hallucination using multi-agent reinforced self-check, enhancing factual consistency in an 8B parameter model.

Zhuo Li, Yupeng Zhang, Pengyu Cheng et al.

Self-distillation can degrade LLMs' reasoning in math by suppressing uncertainty expression.

Jeonghye Kim, Xufang Luo, Minbeom Kim et al.

TiCo method significantly enhances time control in dialogue models using Spoken Time Markers, reducing MAE to 4.54 seconds.

Kai-Wei Chang, Wei-Chih Chen, En-Pei Hu et al.

MemDLM embeds a simulated denoising process into training via bi-level optimization, enhancing DLM training efficiency and long-context understanding.

Zehua Pei, Hui-Ling Zhen, Weizhe Lin et al.

Semantic Token Clustering (STC) method achieves efficient uncertainty quantification in large language models, significantly reducing computational overhead.

Qi Cao, Andrew Gambardella, Takeshi Kojima et al.

Study of SFT-DPO interaction in small models reveals full fine-tuning outperforms LoRA.

Yuming Feng, Christy Yang

F2LLM-v2 offers efficient multilingual embeddings using a two-stage training and matryoshka learning, supporting over 200 languages.

Ziyin Zhang, Zihan Liao, Hang Yu et al.

Nemotron-Cascade 2 achieves top-tier reasoning with Cascade RL and multi-domain distillation in a 30B MoE model.

Zhuolin Yang, Zihan Liu, Yang Chen et al.

VEPO enhances translation quality and tokenization efficiency for low-resource languages using reinforcement learning with verifiable rewards.

Chonghan Liu, Yimin Du, Qi An et al.

Efficient training-free multi-token prediction via embedding-space probing, improving LLaMA3 acceptance length by 12%.

Raghavv Goel, Mukul Gagrani, Mingu Lee et al.

Mixture-of-Depths Attention (MoDA) improves downstream task performance by 2.11% on a 1.5B-parameter model with only a 3.7% increase in FLOPs.

Lianghui Zhu, Yuxin Fang, Bencheng Liao et al.

Correcting moral indifference in language models using Sparse Autoencoders, achieving a 75% win-rate on adversarial benchmarks.

Lingyu Li, Yan Teng, Yingchun Wang

Code-A1 enhances code and test generation through an adversarial co-evolution framework.

Aozhe Wang, Yuchen Yan, Nan Zhou et al.

NAIT framework selects efficient instruction tuning data via neuron activation patterns, enhancing LLM performance.

Xin Chen, Junchao Wu, Shu Yang et al.

ESG-Bench significantly reduces hallucinations in long-context ESG report analysis using task-specific Chain-of-Thought prompting strategies.

Siqi Sun, Ben Peng Wu, Mali Jin et al.