{"total":17,"items":[{"citing_arxiv_id":"2605.12487","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Task-Adaptive Embedding Refinement via Test-time LLM Guidance","primary_cat":"cs.CL","submitted_at":"2026-05-12T17:58:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Test-time LLM feedback refines query embeddings to deliver up to 25% relative gains on zero-shot literature search, intent detection, and related benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07158","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Topic Is Not Agenda: A Citation-Community Audit of Text Embeddings","primary_cat":"cs.IR","submitted_at":"2026-05-08T02:43:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Embeddings retrieve same-subfield papers at 45-52% but same-agenda papers at only 15-21%; citation rerank reaches 57-59% on agenda queries.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04962","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding","primary_cat":"cs.CL","submitted_at":"2026-05-06T14:22:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TabEmbed is the first generalist embedding model for tabular data that unifies classification and retrieval in one space via contrastive learning and outperforms text embedding models on the new TabBench benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04556","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Benchmarking LLMs on the Massive Sound Embedding Benchmark (MSEB)","primary_cat":"cs.SD","submitted_at":"2026-05-06T06:58:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"LLMs exhibit a persistent modality gap versus specialized audio encoders on MSEB tasks, with no conclusive evidence favoring audio-native over cascaded architectures.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01372","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders","primary_cat":"cs.CL","submitted_at":"2026-05-02T10:31:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"EPIC trains LLMs to treat continuous embeddings as in-context prompts, yielding state-of-the-art text embedding performance on MTEB with or without prompts at inference and lower compute.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00063","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Survey of Reasoning-Intensive Retrieval: Progress and Challenges","primary_cat":"cs.IR","submitted_at":"2026-04-30T08:35:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A survey that categorizes RIR benchmarks by domain and modality, proposes a taxonomy for integrating reasoning into retrieval pipelines, and outlines key challenges.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27398","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings","primary_cat":"cs.CL","submitted_at":"2026-04-30T04:09:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Modern text encoders resist second-order collapse under mean pooling because token embeddings concentrate tightly within texts, and this resistance correlates with stronger downstream performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20417","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Semantic Recall for Vector Search","primary_cat":"cs.IR","submitted_at":"2026-04-22T10:34:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Semantic Recall is a new evaluation metric for approximate nearest neighbor search that focuses only on semantically relevant results, with Tolerant Recall as a proxy when relevance labels are unavailable.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19564","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EgoSelf: From Memory to Personalized Egocentric Assistant","primary_cat":"cs.CV","submitted_at":"2026-04-21T15:15:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"EgoSelf uses graph-based memory of user interactions to derive personalized profiles and predict future behaviors for egocentric assistants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18109","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FLiP: Towards understanding and interpreting multimodal multilingual sentence embeddings","primary_cat":"cs.CL","submitted_at":"2026-04-20T11:27:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FLiP recovers more than 75% lexical content from pretrained sentence embeddings across languages and modalities, outperforming non-factorized baselines and exposing intrinsic biases.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17344","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FLARE: Task-agnostic embedding model evaluation through a normalization process","primary_cat":"cs.LG","submitted_at":"2026-04-19T09:31:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FLARE scores embedding models labellessly via normalized log-likelihood, achieving 0.90 Spearman correlation with supervised benchmarks and stable performance in dimensions over 3500 where prior methods collapse.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16826","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Crowded in B-Space: Calibrating Shared Directions for LoRA Merging","primary_cat":"cs.CL","submitted_at":"2026-04-18T04:33:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Pico reduces LoRA merge interference by calibrating over-shared directions in the B matrix before merging, yielding 3.4-8.3 point accuracy gains and sometimes beating joint training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.11801","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CLSGen: A Dual-Head Fine-Tuning Framework for Joint Probabilistic Classification and Verbalized Explanation","primary_cat":"cs.CL","submitted_at":"2026-04-13T17:58:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CLSGen is a dual-head LLM fine-tuning framework that enables joint probabilistic classification and verbalized explanation generation without catastrophic forgetting of generative capabilities.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10389","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection","primary_cat":"cs.CL","submitted_at":"2026-04-12T00:30:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"BLUEmed combines hybrid RAG with structured multi-agent debate and a safety filter to detect terminology substitution errors in clinical notes, reaching 69.13% accuracy under few-shot prompting and outperforming single-agent and debate-only baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.05868","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models","primary_cat":"cs.CL","submitted_at":"2026-04-07T13:28:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Lack of exploration from conditioning on prior answers is the primary reason parallel sampling outperforms sequential sampling in large reasoning models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.04720","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking","primary_cat":"cs.CL","submitted_at":"2026-01-08T08:36:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Qwen3-VL-Embedding-8B achieves state-of-the-art performance with a 77.8 overall score on the MMEB-V2 multimodal embedding benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.05176","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","primary_cat":"cs.CL","submitted_at":"2025-06-05T15:49:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Qwen3 Embedding models in 0.6B-8B sizes achieve state-of-the-art results on MTEB and retrieval tasks including code, cross-lingual, and multilingual retrieval through unsupervised pre-training, supervised fine-tuning, and model merging on Qwen3 backbones.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}