NLPExplorer

EMNLP - 2025

Total Papers:- 2090

Total Papers accross all years:- 14326

Total Citations :- 0

« 84 85 86 87 88 89 90 91 92 93 94 »

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment

The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It

Leonardo Bertolazzi | Philipp Mondorf | Barbara Plank | Raffaella Bernardi |

LightThinker: Thinking Step-by-Step Compression

Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models

Definition Generation for Word Meaning Modeling: Monolingual, Multilingual, and Cross-Lingual Perspectives

Francesco Periti | Roksana Goworek | Haim Dubossarsky | Nina Tahmasebi |

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning

ProCut: LLM Prompt Compression via Attribution Estimation

Zhentao Xu | Fengyi Li | Albert C. Chen | Xiaofeng Wang |

Batched Self-Consistency Improves LLM Relevance Assessment and Ranking

Anton Korikov | Pan Du | Scott Sanner | Navid Rekabsaz |

High-Quality Medical Dialogue Synthesis for Improving EMR Generation

Chengze Ge | Yu Xu | Qi Shao | Shengping Liu |

FIRE: Flexible Integration of Data Quality Ratings for Effective Pretraining

Mitigating Biases in Language Models via Bias Unlearning

Dianqing Liu | Yi Liu | Guoqing Jin | Zhendong Mao |

Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models

Younwoo Choi | Changling Li | Yongjin Yang | Zhijing Jin |

Robust Native Language Identification through Agentic Decomposition

Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model