{"total":14,"items":[{"citing_arxiv_id":"2606.13647","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation","primary_cat":"cs.CL","submitted_at":"2026-06-11T17:50:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"SkMTEB is the first comprehensive text embedding benchmark for Slovak, and vocabulary-trimmed E5 adaptations achieve competitive performance with much smaller models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07923","ref_index":73,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Larch: Learned Query Optimization for Semantic Predicates","primary_cat":"cs.DB","submitted_at":"2026-06-06T01:16:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Larch uses a GNN-MDP formulation and a selectivity predictor plus dynamic programming to reorder semantic filter evaluation, cutting token usage 3x-19x versus prior systems on real and synthetic workloads.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29960","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction","primary_cat":"cs.CR","submitted_at":"2026-05-28T14:02:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MemPoison enables stealthy memory poisoning in LLM agents via dialogue by using semantic relational bridges, entity masquerading, and joint embedding optimization to bypass selective extraction and rewriting, achieving up to 0.95 attack success rate.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27168","ref_index":70,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Grounding Text Embeddings in Stakeholder Associations","primary_cat":"cs.CL","submitted_at":"2026-05-26T15:24:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The Stakeholder Grounding Exercise shows neural text embeddings are 19-26pp less reliable than human experts at capturing semantic distinctions, with misalignment strongly correlated to poorer clustering performance (ρ=0.9), replicated across Danish policy and US AI domains.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.25030","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration","primary_cat":"cs.LG","submitted_at":"2026-05-24T12:15:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"MimirRAG, a multi-agent RAG framework with metadata integration and table-aware chunking, reaches 89.3% accuracy on FinanceBench and outperforms prior baselines for financial document retrieval.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22202","ref_index":138,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance","primary_cat":"cs.CL","submitted_at":"2026-05-21T09:05:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Embedding model performance on MTEB tasks correlates strongly with nearest-neighbor overlap and ICA magnitude differences in their embedding spaces.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12714","ref_index":76,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs","primary_cat":"cs.LG","submitted_at":"2026-05-12T20:22:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LRD framework with Frenet, NRS, and GFMI metrics shows layer-wise structure in 31 models provides usable signal for model selection and pruning on MTEB tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07249","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal","primary_cat":"cs.IR","submitted_at":"2026-05-08T05:10:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MLAIRE is a protocol that evaluates multilingual retrievers on both semantic accuracy and query-language preference using parallel passages and new metrics like LPR and Lang-nDCG, showing that standard metrics hide distinct behavioral differences among retrievers.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"selection prioritizes breadth across paradigms and model scales, and includes widely used or recently released publicly available multilingual retrievers at the time of our experiments. DenseOur dense retrievers encompass diverse model lineages, ranging from widely adopted encoder-only families such as multilingual-e5 [ 32], bge-m3 [33], gte [34], snowflake-arctic [35], nomic-embed [36], embeddinggemma [37] and jina [38, 39], to recent LLM-based embedding models including Qwen3-Embedding [40], llama-nemotron [41], and pplx-embed [42]. In this paradigm, queries and passages are independently encoded into fixed-dimensional vectors and scored by cosine similarity. We use each model's prescribed pooling strategy (CLS, mean, or last-token) and follow"},{"citing_arxiv_id":"2605.05251","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Identifier-Free Code Embedding Models for Scalable Search","primary_cat":"cs.CR","submitted_at":"2026-05-05T17:53:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A fine-tuned Qwen3-Embedding model with contrastive learning outperforms baselines on bidirectional source-to-decompiled code association and generalizes to constant-algorithm tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14907","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task","primary_cat":"cs.CL","submitted_at":"2026-04-16T11:49:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Supervised models using embeddings like jina and e5 reach up to 92% accuracy on multilingual hate speech detection, substantially outperforming anomaly detection, while PCA to 64 dimensions preserves most performance in the supervised case.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"documented instances of online hate speech in the Lithuanian digital sphere, systematic studies on automated hate speech detection in Lithuanian have only recently begun to appear in the literature [25]. Second, modern multilingual sentence embedding models have emerged as a promising paradigm for cross-lingual and multilingual text classification tasks. Models such as Multilingual E5 [26], Jina Embeddings [27], Snowflake Arctic [28], and BGE-M3 [29] encode texts from dozens or hundreds of languages into a shared vector space, enabling downstream classifiers to operate on fixed-dimensional representations without requiring language-specific fine-tuning. However, systematic comparisons of these modern off-the-shelf embedding models for hate speech detection - particularly in multilingual settings that include low-resource languages - remain scarce."},{"citing_arxiv_id":"2602.15547","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"jina-embeddings-v5-text: Task-Targeted Embedding Distillation","primary_cat":"cs.CL","submitted_at":"2026-02-17T12:50:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A distillation-plus-task-contrastive training regimen yields compact embedding models that match or exceed state-of-the-art performance for their size while supporting 32k-token contexts and quantization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.14274","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Retrofitting Small Multilingual Models for Retrieval: Matching 7B Performance with 300M Parameters","primary_cat":"cs.CL","submitted_at":"2025-10-16T03:48:59+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A 300M multilingual embedding model matches or exceeds 7B retrieval performance via optimized data scale, hard negatives, and task diversity over language diversity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.12539","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations","primary_cat":"cs.IR","submitted_at":"2025-09-16T00:41:05+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LEAF distills teacher-aligned student embedding models that achieve new SOTA results on BEIR and MTEB for their size class while requiring only modest data and compute.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.03122","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Federated Learning for ICD Classification with Lightweight Models and Pretrained Embeddings","primary_cat":"cs.IR","submitted_at":"2025-07-03T18:58:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Lightweight federated learning with frozen embeddings and MLP heads reaches competitive micro and macro F1 scores for ICD-9 and ICD-10 coding on MIMIC-IV, nearly matching centralized training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}