mlsanityData to 13 Oct 2026

SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation

arXiv 2410.11315 ↗First posted 15 Oct 2024cs.CLcited by 9

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

also in 1 more
Abstract (arXiv)

Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG performance, yet it remains challenging. Existing methods heavily rely on heuristic-based augmentation, encountering several issues: (1) Poor generalization due to hand-crafted context filtering; (2) Semantics deficiency due to rule-based context chunking; (3) Skewed length due to sentence-wise filter learning. To address these issues, we propose a model-based evidence extraction learning framework, SEER, optimizing a vanilla model as an evidence extractor with desired properties through self-aligned learning. Extensive experiments show that our method largely improves the final RAG performance, enhances the faithfulness, helpfulness, and conciseness of the extracted evidence, and reduces the evidence length by 9.25 times. The code will be available at https://github.com/HITsz-TMG/SEER.

Key facts. Cited by 9 papers in the map (data through 13 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 33 of its 51 references that are in the map. First posted on arXiv 15 Oct 2024.

Builds on

33 of 51 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence19 Feb

Other references · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2017Proximal Policy Optimization Algorithmscited by 14,592
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,979
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,221
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,107
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,797
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,716
  8. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,011
  9. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,925
  10. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,196
  11. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,131
  12. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 960
20 more
  1. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 898
  2. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 829
  3. 2023In-Context Retrieval-Augmented Language Modelscited by 699
  4. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 693
  5. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 527
  6. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 447
  7. 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervisioncited by 318
  8. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 285
  9. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
  10. 2023Almanac: Retrieval-Augmented Language Models for Clinical Medicinecited by 123
  11. 2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
  12. 2024LiPO: Listwise Preference Optimization through Learning-to-Rankcited by 96
  13. 2024Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluationcited by 80
  14. 2021Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Featurescited by 74
  15. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  16. 2019Knowledge Guided Text Retrieval and Reading for Open Domain Question Answeringcited by 59
  17. 2024Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigationcited by 43
  18. 2020Multi-Loss Weighting with Coefficient of Variationscited by 36
  19. 2024Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answeringcited by 9
  20. 2021Natural Answer Generation: From Factoid Answer to Full-length Answer using Grammar Correctioncited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 4.

9 papers.

  1. 2024ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Explorationcited by 101
  2. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  3. 2025KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Modelcited by 35
  4. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontierscited by 27
  5. 2024ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAGcited by 6
  6. 2026LMEB: Long-horizon Memory Embedding Benchmarkcited by 6
  7. 2026Fixed RAG Compression Collapses Measured Reader Scalingcited by 1
  8. 2026Beyond Relevance: Utility-Centric Retrieval in the LLM Eracited by 0
  9. 2026Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Rerankingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Assessing the Downstream Utility of Evidence-Aware Retrieval in RAG
  2. 2026REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving
  3. 2026Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning
  4. 2025KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG
  5. 2026Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selection
  6. 2026Candidate-Constrained Retrieval-Augmented Generation for LongEval-RAG: System Design and Empirical Analysis
  7. 2026ERA: Evidence-based Reliability Alignment for Honest Retrieval-Augmented Generation
  8. 2026Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG