{"total":18,"items":[{"citing_arxiv_id":"2605.08809","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization","primary_cat":"cs.CL","submitted_at":"2026-05-09T08:59:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SimReg regularization accelerates LLM pretraining convergence by over 30% and raises average zero-shot performance by over 1% across benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04962","ref_index":8,"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":"2605.04295","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LLMs Uncertainty Quantification via Adaptive Conformal Semantic Entropy","primary_cat":"cs.LG","submitted_at":"2026-05-05T20:56:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ACSE estimates LLM prompt uncertainty via adaptive clustering of semantic entropy across multiple responses and uses conformal prediction to bound error rates on accepted answers with distribution-free guarantees.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.25853","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"G-Loss: Graph-Guided Fine-Tuning of Language Models","primary_cat":"cs.CL","submitted_at":"2026-04-28T16:55:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"G-Loss builds a document-similarity graph and uses semi-supervised label propagation to guide fine-tuning of language models, yielding higher accuracy than standard losses on five classification benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24374","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining","primary_cat":"cs.CL","submitted_at":"2026-04-27T12:07:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MIPIC trains nested Matryoshka representations via self-distilled intra-relational alignment with top-k CKA and progressive information chaining across depths, yielding competitive performance especially at extreme low dimensions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20417","ref_index":11,"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":"2604.17725","ref_index":121,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models","primary_cat":"cs.CL","submitted_at":"2026-04-20T02:20:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RePrompT uses recurrent prompt tuning to inject prior-visit latent states and cohort-derived population prompt tokens into LLMs, yielding better performance than pure EHR or pure LLM baselines on MIMIC clinical prediction tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17214","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond the Basics: Leveraging Large Language Model for Fine-Grained Medical Entity Recognition","primary_cat":"cs.AI","submitted_at":"2026-04-19T02:50:14+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Fine-tuned LLaMA3 with LoRA reaches 81.24% F1 on 18-category fine-grained medical entity recognition, beating zero-shot by 63.11% and few-shot by 35.63%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17054","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval","primary_cat":"cs.CV","submitted_at":"2026-04-18T16:23:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"mEOL creates aligned embeddings for text, images, and SVGs using instruction-guided MLLM one-word summaries and semantic SVG rewriting, outperforming baselines on a new text-to-SVG retrieval benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16678","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UniCon: Unified Framework for Efficient Contrastive Alignment via Kernels","primary_cat":"cs.LG","submitted_at":"2026-04-17T20:21:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UniCon unifies contrastive alignment across encoders and alignment types using kernels to enable exact closed-form updates instead of stochastic optimization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10721","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Turning Generators into Retrievers: Unlocking MLLMs for Natural Language-Guided Geo-Localization","primary_cat":"cs.CV","submitted_at":"2026-04-12T16:40:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Parameter-efficient fine-tuning lets MLLMs serve as effective retrievers for natural-language-guided cross-view geo-localization, beating dual-encoder baselines on GeoText-1652 and CVG-Text while using far fewer trainable parameters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10590","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance","primary_cat":"cs.CL","submitted_at":"2026-04-12T11:43:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A new pre-training task that maps languages bidirectionally in embedding space improves machine translation by up to 11.9 BLEU, cross-lingual QA by 6.72 BERTScore points, and understanding accuracy by over 5% over strong baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.06163","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Data, Not Model: Explaining Bias toward LLM Texts in Neural Retrievers","primary_cat":"cs.IR","submitted_at":"2026-04-07T17:57:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Bias toward LLM texts in neural retrievers arises from artifact imbalances between positive and negative documents in training data that are absorbed during contrastive learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.26955","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Policy-Governed LLM Routing with Intent Matching for Instrument Laboratories","primary_cat":"cs.CY","submitted_at":"2026-04-03T15:36:29+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A governed LLM routing system for lab tutoring raises challenge-alignment from 0.90 to 0.98, boosts productive-struggle time, and cuts token costs by two-thirds while preserving answer accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2402.03216","ref_index":56,"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},{"citing_arxiv_id":"2311.05232","ref_index":99,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","primary_cat":"cs.CL","submitted_at":"2023-11-09T09:25:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"and PARENT-T [324], typically fall short in differentiating the nuanced discrepancies between the generated content and the source content [208]. Entity-based metrics [225] make a step further by calculating the overlap of entities, as any omission or inaccurate generation of these key entities could lead to an unfaithful response. Notably, even if entities match, the relations between them might be erroneous. Thus, relation-based metrics [99] focus on the overlap of relation tuples and introduce a metric that computes the overlap of relation tuples extracted using trained end-to-end fact extraction models. Classifier-based Metrics. Beyond computing fact overlap, another straightforward approach to assessing the faithfulness of the model generation involves utilizing classifiers trained on data"},{"citing_arxiv_id":"2305.06161","ref_index":121,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"StarCoder: may the source be with you!","primary_cat":"cs.CL","submitted_at":"2023-05-09T08:16:42+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2112.09118","ref_index":131,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Unsupervised Dense Information Retrieval with Contrastive Learning","primary_cat":"cs.IR","submitted_at":"2021-12-16T18:57:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Contrastive learning trains unsupervised dense retrievers that beat BM25 on most BEIR datasets and support cross-lingual retrieval across scripts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}