mlsanityData to 7 Oct 2026

Science Checker Reloaded: A Bidirectional Paradigm for Transparency and Logical Reasoning

arXiv 2402.13897 ↗First posted 21 Feb 2024cs.IR cs.AI cs.CLcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Information retrieval is a rapidly evolving field. However it still faces significant limitations in the scientific and industrial vast amounts of information, such as semantic divergence and vocabulary gaps in sparse retrieval, low precision and lack of interpretability in semantic search, or hallucination and outdated information in generative models. In this paper, we introduce a two-block approach to tackle these hurdles for long documents. The first block enhances language understanding in sparse retrieval by query expansion to retrieve relevant documents. The second block deepens the result by providing comprehensive and informative answers to the complex question using only the information spread in the long document, enabling bidirectional engagement. At various stages of the pipeline, intermediate results are presented to users to facilitate understanding of the system's reasoning. We believe this bidirectional approach brings significant advancements in terms of transparency, logical thinking, and comprehensive understanding in the field of scientific information retrieval.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 20 of its 38 references that are in the map. First posted on arXiv 21 Feb 2024.

Builds on

20 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks28 Apr

Other references · 19

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  3. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  4. 2022MTEB: Massive Text Embedding Benchmarkcited by 623
  5. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
  6. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  7. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 160
  8. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 92
  9. 2023A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challengecited by 55
  10. 2023Text2KGBench: A Benchmark for Ontology-Driven Knowledge Graph Generation from Textcited by 48
  11. 2023Understanding Retrieval Augmentation for Long-Form Question Answeringcited by 45
  12. 2023RETA-LLM: A Retrieval-Augmented Large Language Model Toolkitcited by 40
7 more
  1. 2023A Cost Analysis of Generative Language Models and Influence Operationscited by 17
  2. 2023Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoningcited by 16
  3. 2021Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selectioncited by 15
  4. 2023Reducing LLM Hallucinations using Epistemic Neural Networkscited by 8
  5. 2018An Ontology-Based Dialogue Management System for Banking and Finance Dialogue Systemscited by 7
  6. 2021Automatic Claim Review for Climate Science via Explanation Generationcited by 4
  7. 2022KGI: An Integrated Framework for Knowledge Intensive Language Taskscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval
  2. 2026DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering
  3. 2025SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMs
  4. 2026Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning Capabilities
  5. 2023Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning
  6. 2025HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights
  7. 2025Enhancing Retrieval Systems with Inference-Time Logical Reasoning
  8. 2026VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy