{"total":27,"items":[{"citing_arxiv_id":"2606.24094","ref_index":80,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent","primary_cat":"cs.CV","submitted_at":"2026-06-23T03:20:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A hybrid LLM agent framework performs universal image clustering by generating guideline-aware embeddings via concept proxies and using MST-based LLM traversal for automatic discovery.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23791","ref_index":239,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"One Generator, Any Process: LLM-Conditioning for the LHC","primary_cat":"hep-ph","submitted_at":"2026-06-22T18:00:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LLM embeddings condition a generative transformer to enable faster convergence, better performance, and generalization to unseen LHC processes using a single model.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23642","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Improving Long-Context Retrieval with Multi-Prefix Embedding","primary_cat":"cs.IR","submitted_at":"2026-06-22T17:31:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Multi-Prefix Embedding extracts per-chunk embeddings from a single forward pass over EOS-separated document chunks and matches via MaxSim while training only on document-level labels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.13680","ref_index":51,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning","primary_cat":"cs.CL","submitted_at":"2026-06-11T17:59:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RA-RFT trains a retriever to rank contexts by expected reasoning benefit and uses the retrieved analogies inside reinforcement fine-tuning, yielding 7.1 and 2.8 point gains on AIME 2025 over GRPO for two Qwen3 models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.13061","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck","primary_cat":"cs.CV","submitted_at":"2026-06-11T08:47:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LaME performs latent multimodal embedding reasoning with K learnable reason tokens in a weakly supervised information bottleneck, matching some explicit CoT models while running 60x faster.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01504","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Semantic Retrieval for Product Search in E-Commerce","primary_cat":"cs.IR","submitted_at":"2026-05-31T23:59:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A dual-encoder LLM is trained via contrastive learning then ROAR to retrieve exact matches and rank substitutes in e-commerce search.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22202","ref_index":130,"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":"2605.21071","ref_index":49,"ref_count":3,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fine-grained Claim-level RAG Benchmark for Law","primary_cat":"cs.CL","submitted_at":"2026-05-20T11:56:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ClaimRAG-LAW is a French-English legal RAG benchmark with claim-level granularity for experts and non-experts that reveals limitations in current retrieval and generation performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18007","ref_index":98,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling","primary_cat":"cs.CL","submitted_at":"2026-05-18T08:03:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"RISE is an inference-time semantic reranking framework that refines low-confidence predictions in rhetorical role labeling using contrastively learned label representations, delivering an average +9.15 macro-F1 gain on hard examples across eight datasets and seven models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14503","ref_index":47,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks","primary_cat":"cs.SE","submitted_at":"2026-05-14T07:47:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14061","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MathAtlas: A Benchmark for Autoformalization in the Wild","primary_cat":"cs.AI","submitted_at":"2026-05-13T19:35:46+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":8.0,"formal_verification":"none","one_line_summary":"MathAtlas is the first large-scale benchmark for autoformalizing graduate mathematics, where even strong models reach only 9.8% correctness on theorem statements and drop to 2.6% on the hardest dependency-deep subset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11374","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Test-Time Compute for Frozen Embedding Models through Agentic Program Search","primary_cat":"cs.LG","submitted_at":"2026-05-12T00:56:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Agentic program search over a frozen encoder API yields retrieval programs that improve nDCG@10 on held-out tasks and unseen encoder families with no per-domain training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00618","ref_index":75,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Is Textual Similarity Invariant under Machine Translation? Evidence Based on the Political Manifesto Corpus","primary_cat":"cs.CL","submitted_at":"2026-05-01T12:41:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Machine translation preserves embedding similarity structure for ten languages but distorts it for four in the Manifesto Corpus, via a new non-inferiority testing framework.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22861","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review","primary_cat":"cs.IR","submitted_at":"2026-04-23T01:55:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"IntrAgent uses a two-stage pipeline of section ranking and iterative reading to perform content-grounded literature information retrieval, achieving 13.2% higher accuracy than RAG and agent baselines on the new IntraBench benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09019","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Regime-Conditional Retrieval: Theory and a Transferable Router for Two-Hop QA","primary_cat":"cs.IR","submitted_at":"2026-04-10T06:31:51+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Two-hop QA retrieval performance depends on whether the hop-2 entity is in the question or bridge passage, and a simple predicate-based router trained on one dataset transfers to improve R@5 on others.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.26815","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off","primary_cat":"cs.CL","submitted_at":"2026-03-26T18:05:38+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.14348","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Legal Retrieval for Public Defenders","primary_cat":"cs.IR","submitted_at":"2026-01-20T17:08:34+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"NJ BriefBank is a domain-adapted legal retrieval tool for public defenders that improves on standard benchmarks by incorporating legal reasoning, domain data, and synthetic examples, with a new released taxonomy and annotated evaluation dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.07969","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Unified Work Embeddings: Contrastive Learning of a Bidirectional Multi-task Ranker","primary_cat":"cs.CL","submitted_at":"2025-11-11T08:28:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"UWE is a task-agnostic bi-encoder that uses many-to-many InfoNCE and token-level soft late interaction to achieve zero-shot ranking across unseen work-related target spaces while using far fewer parameters than Qwen3-8B and improving MAP by 4.4 points.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.14274","ref_index":12,"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":"2507.08480","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging","primary_cat":"cs.IR","submitted_at":"2025-07-11T10:44:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Language composition in training data creates opposing effects on CLIR and mono-IR performance for Korean-English retrieval, which model merging can partially resolve.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.04590","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents","primary_cat":"cs.CV","submitted_at":"2025-07-07T00:51:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"VLM2Vec-V2 is a multimodal embedding model trained on an extended MMEB-V2 benchmark that adds video and visual document tasks and reports gains on both new and prior image benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2410.22240","ref_index":38,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Are Decoder-Only Large Language Models the Silver Bullet for Code Search?","primary_cat":"cs.SE","submitted_at":"2024-10-29T17:05:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Fine-tuned decoder-only LLMs achieve up to 40.4% higher MAP than UniXcoder on CoSQA+ for code search, with non-monotonic size scaling and data composition sensitivity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2407.12580","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"E5-V: Universal Embeddings with Multimodal Large Language Models","primary_cat":"cs.CL","submitted_at":"2024-07-17T14:04:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"E5-V produces strong universal multimodal embeddings from MLLMs trained solely on text pairs, often surpassing prior methods across retrieval and related tasks without multimodal fine-tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2405.17428","ref_index":99,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:59:45+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2404.18796","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models","primary_cat":"cs.CL","submitted_at":"2024-04-29T15:33:23+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A panel of smaller diverse LLMs outperforms a single large model as an evaluator of generations, showing less intra-model bias and over 7x lower cost.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2402.05672","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multilingual E5 Text Embeddings: A Technical Report","primary_cat":"cs.CL","submitted_at":"2024-02-08T13:47:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Open-source multilingual E5 embedding models are trained via contrastive pre-training on 1 billion text pairs and fine-tuning, with an instruction-tuned model matching English SOTA performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2402.03216","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","primary_cat":"cs.CL","submitted_at":"2024-02-05T17:26:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual, and long-document retrieval benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}