Retrieval coverage limits LLM rerankers in cold-start recommendation; a learned hybrid fusion improves pool quality but LLM reranking often degrades end-to-end performance while simpler rankers exploit the pool.
hub
A., and Buettcher, Stefan
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
hub tools
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
LongBEL improves biomedical entity linking consistency by combining full-document context with memory of previous predictions trained via cross-validation rather than gold labels.
LLM adaptive exploration via runtime code execution outperforms static query generation for information extraction from heterogeneous BIM models on the new ifc-bench v2 benchmark.
Semantic stratification organizes documents into entity-based clusters to systematically generate queries for missing strata, yielding formal coverage guarantees and interpretable failure mode visibility in retrieval evaluation.
MatClaw shows a code-first LLM agent autonomously generating and executing workflows for ML force field training, Curie temperature prediction, and parameter search on CuInP2S6, succeeding on code but requiring interventions for tacit domain knowledge.
A framework decomposes LLM papers into idea atoms, trains coherence and availability models over the resulting vocabulary, and samples atom combinations that are coherent yet unlikely under existing author communities.
A retrieve-then-confirm framework applied to one CS program finds ~50% coverage of both CS2013 and CS2023, ~88% competency articulation, and lower cognitive depth under the newer guideline (76% vs 95%).
Agentic hybrid RAG with a new muon collider benchmark outperforms baselines in retrieval effectiveness, answer quality, evidence coverage, and factual grounding.
Introduces a matched four-condition protocol and ONCU metric to diagnose evidence utilization in long-context and RAG models across synthetic and multi-hop QA tasks.
Large-scale evaluation shows retrieval-augmented generation yields only marginal and inconsistent gains (1-2 points) over no-retrieval baselines in biomedical QA, with model choice dominating retriever or corpus effects.
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.
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
Attention-based models can retrieve evidence intrinsically by using decoder attention to score and reuse their own pre-encoded chunks, outperforming separate retrieval pipelines on QA benchmarks.
Introduces a reproducible benchmark and hybrid sparse-dense retrieval framework for evidence-grounded access to silicon detector literature, reporting Hit@5 of 0.917 on core queries.
Constrained candidate selection from retrieved chunks raises Recall@5 from 31.9% to 50.0% and parseable outputs on 420 queries from 200 municipal meeting transcripts.
CMIP-Forge presents a retrieval-augmented agentic system with automated guardrails and adversarial self-review for autonomous execution of climate research tasks on CMIP6 literature and ESGF data.
OMAGR decomposes queries into ontology-aligned anchors for parallel multi-dimensional graph retrieval, outperforming baselines on Context Precision and Faithfulness in the new TrafficLaw-QA dataset of 200 questions.
Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.
ELERAG integrates Wikidata entity linking with hybrid RRF re-ranking into RAG and outperforms baselines on a custom Italian academic dataset while cross-encoder methods win on the general SQuAD-it dataset.
Agentic-J is a multi-agent AI assistant that converts natural language descriptions of biological image analysis tasks into executable, reproducible scripts for ImageJ/Fiji with specialised sub-agents for plugin management, code generation, debugging and reporting.
A two-stage hybrid search pipeline paired with a synthetic-data fine-tuned and compressed Ukrainian language model delivers competitive local question answering under strict compute limits.
Proposes a privacy-preserving RAG system using LLMs and syllabus data for academic advising on course sequences and personalized planning.
citing papers explorer
-
Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation
Retrieval coverage limits LLM rerankers in cold-start recommendation; a learned hybrid fusion improves pool quality but LLM reranking often degrades end-to-end performance while simpler rankers exploit the pool.
-
LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking
LongBEL improves biomedical entity linking consistency by combining full-document context with memory of previous predictions trained via cross-validation rather than gold labels.
-
BIM Information Extraction Through LLM-based Adaptive Exploration
LLM adaptive exploration via runtime code execution outperforms static query generation for information extraction from heterogeneous BIM models on the new ifc-bench v2 benchmark.
-
Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation
Semantic stratification organizes documents into entity-based clusters to systematically generate queries for missing strata, yielding formal coverage guarantees and interpretable failure mode visibility in retrieval evaluation.
-
MatClaw: An Autonomous Code-First LLM Agent for End-to-End Materials Exploration
MatClaw shows a code-first LLM agent autonomously generating and executing workflows for ML force field training, Curie temperature prediction, and parameter search on CuInP2S6, succeeding on code but requiring interventions for tacit domain knowledge.
-
The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions
A framework decomposes LLM papers into idea atoms, trains coherence and availability models over the resulting vocabulary, and samples atom combinations that are coherent yet unlikely under existing author communities.
-
Measuring Curriculum Alignment across Topical Coverage, Competency, and Cognitive Depth: A Longitudinal Framework Applied to CS2013 and CS2023
A retrieve-then-confirm framework applied to one CS program finds ~50% coverage of both CS2013 and CS2023, ~88% competency articulation, and lower cognitive depth under the newer guideline (76% vs 95%).
-
Agentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis
Agentic hybrid RAG with a new muon collider benchmark outperforms baselines in retrieval effectiveness, answer quality, evidence coverage, and factual grounding.
-
Diagnosing Evidence Utilization in Long-Context and Retrieval-Augmented Language Models under Matched Evidence Conditions
Introduces a matched four-condition protocol and ONCU metric to diagnose evidence utilization in long-context and RAG models across synthetic and multi-hop QA tasks.
-
When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG
Large-scale evaluation shows retrieval-augmented generation yields only marginal and inconsistent gains (1-2 points) over no-retrieval baselines in biomedical QA, with model choice dominating retriever or corpus effects.
-
Test-Time Compute for Frozen Embedding Models through Agentic Program Search
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.
-
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
-
Retrieval from Within: An Intrinsic Capability of Attention-Based Models
Attention-based models can retrieve evidence intrinsically by using decoder attention to score and reuse their own pre-encoded chunks, outperforming separate retrieval pipelines on QA benchmarks.
-
A Reproducible Benchmark and Evidence-Retrieval Software Framework for Silicon Detector R&D Literature
Introduces a reproducible benchmark and hybrid sparse-dense retrieval framework for evidence-grounded access to silicon detector literature, reporting Hit@5 of 0.917 on core queries.
-
Topic-to-Timestamp Alignment by Constrained Evidence Selection
Constrained candidate selection from retrieved chunks raises Recall@5 from 31.9% to 50.0% and parseable outputs on 420 queries from 200 municipal meeting transcripts.
-
CMIP-Forge: An Agentic System that Retrieves, Computes, and Self-Reviews Climate Science
CMIP-Forge presents a retrieval-augmented agentic system with automated guardrails and adversarial self-review for autonomous execution of climate research tasks on CMIP6 literature and ESGF data.
-
An Ontology-Guided Multi-Anchor Graph Retrieval Framework for Traffic Legal Liability Determination
OMAGR decomposes queries into ontology-aligned anchors for parallel multi-dimensional graph retrieval, outperforming baselines on Context Precision and Faithfulness in the new TrafficLaw-QA dataset of 200 questions.
-
Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks
Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.
-
Enhancing Retrieval-Augmented Generation with Entity Linking for Educational Platforms
ELERAG integrates Wikidata entity linking with hybrid RRF re-ranking into RAG and outperforms baselines on a custom Italian academic dataset while cross-encoder methods win on the general SQuAD-it dataset.
-
Agentic-J: An AI Agent for Biological Microscopy Image Analysis
Agentic-J is a multi-agent AI assistant that converts natural language descriptions of biological image analysis tasks into executable, reproducible scripts for ImageJ/Fiji with specialised sub-agents for plugin management, code generation, debugging and reporting.
-
An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation
A two-stage hybrid search pipeline paired with a synthetic-data fine-tuned and compressed Ukrainian language model delivers competitive local question answering under strict compute limits.
-
A Locally Deployed RAG-Based Academic Advising System for Course Selection
Proposes a privacy-preserving RAG system using LLMs and syllabus data for academic advising on course sequences and personalized planning.