跳转至

EMNLP 2025 · 全部收录(315 篇)

仅列出通过预过滤且已打分的论文;分数是「评测方法学价值」,不是会议录用质量。 返回总览

# 论文 轨道 分数 链接
301 Retrieval-Augmented Generation with Estimation of Source Reliability Main 4 页 · PDF
302 Surprise Calibration for Better In-Context Learning Main 4 页 · PDF
303 The Sound of Syntax: Finetuning and Comprehensive Evaluation of Language Models for Speech Pathology Main 4 页 · PDF
304 Trustworthy Medical Question Answering: An Evaluation-Centric Survey Main 4 页 · PDF
305 Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments Main 4 页 · PDF
306 Expectation Preference Optimization: Reliable Preference Estimation for Improving the Reasoning Capability of Large Language Models Main 3 页 · PDF
307 GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models Main 3 页 · PDF
308 HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation Main 3 页 · PDF
309 Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation Main 3 页 · PDF
310 SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models Main 3 页 · PDF
311 Temporal Scaling Law for Large Language Models Main 3 页 · PDF
312 Calibrating Pseudo-Labeling with Class Distribution for Semi-supervised Text Classification Main 2 页 · PDF
313 How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models Main 2 页 · PDF
314 Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models Main 2 页 · PDF
315 Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? Main 2 页 · PDF

评论