# ECI_{sem}：面向困难负样本评估的语义残差有效对比信息方法

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-05 08:00
- AIHOT 分数：61
- AIHOT 链接：https://aihot.virxact.com/items/cmq5os9av00ywsl5ifc9o4sbk
- 原文链接：https://arxiv.org/abs/2603.20990

## AI 摘要

提出ECI_{sem}，一种无需训练的语义残差变体，利用冻结目标编码器嵌入对密集检索候选负样本源排序。每个评分需查询、标注正例及显式候选负例。ECI_{sem}从目标一致性、语义局部性、词汇残差性和对数行列式多样性构建加权残差信息矩阵。在MS MARCO上，族内ECI_{sem}将LLM负样本（非混合）和Dense+LLM（混合源）排为最高，与DistilBERT、E5-base、Contriever在BEIR上的最强聚合迁移结果一致。消融实验表明对齐依赖目标编码器族，且在样本量、温度等扰动下稳定。

## 正文

Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation. We propose ECI_{sem}, a semantic residual variant of Effective Contrastive Information (ECI) that ranks candidate negative sources using frozen target-encoder embeddings. ECI_{sem} is training-free, not label-free: each scored example requires a query, a labeled positive, and an explicit candidate negative. ECI_{sem} builds a weighted residual information matrix from target consistency, semantic locality, lexical residuality, and a log-determinant diversity objective. On MS MARCO negative sources, in-family ECI_{sem} ranks LLM negatives highest among non-hybrid sources and Dense+LLM highest among hybrid sources, matching the strongest aggregate BEIR transfer results across DistilBERT, E5-base, and Contriever. Controlled ablations show that this alignment depends on using the target encoder family, while additional ablations show stability under sample-size, temperature, tokenizer, and IDF-corpus perturbations. The theory gives a local linearized link to loss reduction, while the empirical study treats downstream evaluation as the final test.