←Search results

Search “Search”

By relevance · Total 6 results Clear search

Friday

  1. Unite.AI

    Imperial College London paper: search-augmented LLMs often cite web pages they never opened

    Three authors from Imperial College London have published the paper "Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence," examining why search-augmented LLMs frequently cite web pages they never actually open. The study tested GPT-5.6 Luna and six open-weight configurations including GLM-5.3-Flash, gpt-oss-120b, gpt-oss-20b, gemma-4-31b, and qwen3-8b using 225 facts that changed after February 16, 2026, finding that models often answer based solely on search snippets without opening the source pages; under the same set of search results, the proportion of cases where no page was opened ranged from 2.6% to 76%, and when Luna used its built-in search, 53.6% of turns relied only on snippets. When answering from snippets alone, outdated answers accounted for 6.4% and misleading citations for 6.4%, whereas when pages were opened and cited, these fell to 1.3% and 2.3% respectively; placing the correct page directly into the prompt significantly reduced errors, but some models still favored old information even when shown the new facts.

    Three authors from Imperial College London have published the paper "Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence," examining why search-augmented LLMs frequently cite web pages they never actually open. The study tested GPT-5.6 Luna and six open-weight configurations including GLM-5.3-Flash, gpt-oss-120b, gpt-oss-20b, gemma-4-31b, and qwen3-8b using 225 facts that changed after February 16, 2026, finding that models often answer based solely on

    Matched fieldsTitle

    #hot-signal#Papers/Research#RAG#Evaluations / benchmarks
  2. FactRelated story

    Imperial College study reveals that search-augmented LLMs cite sources without reading them

    On October 16, 2026, three authors from the Department of Computing at Imperial College London published the paper "Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence," investigating why search-augmented LLMs frequently cite web pages they never actually opened. The study tested six open-weight configurations—GPT-5.6 Luna, GLM-5.3-Flash, gpt-oss-120b, gpt-oss-20b, gemma-4-31b, and qwen3-8b—using 225 facts that changed after February 16, 2026. The results showed that models often answer based solely on search snippets without opening the source pages; under the same set of search results, the proportion of turns in which no page was opened ranged from 2.6% to 76%, and when Luna used its built-in search, 53.6% of turns relied only on snippets. When answering from snippets alone, outdated answers accounted for 6.4% and misleading citations for 6.4%; when pages were opened and cited, these two figures dropped to 1.3% and 2.3%, respectively. The study also found that placing the correct page directly into the prompt significantly reduced errors, but some models still favored old information even when shown new facts. Currently, this research has been reported by a single source, with no subsequent developments yet.

    Matched fieldsTitle

    View story:Imperial College London Study Reveals Search-Augmented LLMs Cite Sources Without Reading Them

Friday

Sunday

  1. Story1 reports · 1 facts

    Imperial College London Study Reveals Search-Augmented LLMs Cite Sources Without Reading Them

    On October 16, 2026, three authors from the Department of Computing at Imperial College London published the paper "Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence," investigating why search-augmented LLMs frequently cite web pages they never actually opened. The study tested six open-weight configurations—GPT-5.6 Luna, GLM-5.3-Flash, gpt-oss-120b, gpt-oss-20b, gemma-4-31b, and qwen3-8b—using 225 facts that changed after February 16, 2026. The results showed that models often answer based solely on search snippets without opening the source pages; under the same set of search results, the proportion of turns in which no page was opened ranged from 2.6% to 76%, and when Luna used its built-in search, 53.6% of turns relied only on snippets. When answering from snippets alone, outdated answers accounted for 6.4% and misleading citations for 6.4%; when pages were opened and cited, these two figures dropped to 1.3% and 2.3%, respectively. The study also found that placing the correct page directly into the prompt significantly reduced errors, but some models still favored old information even when shown new facts. Currently, this research has been reported by a single source, with no subsequent developments yet.

    On October 16, 2026, three authors from the Department of Computing at Imperial College London published the paper "Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence," investigating why search-augmented LLMs frequently cite web pages they never actually opened. The study tested six open-weight configurations—GPT-5.6 Luna, GLM-5.3-Flash, gpt-oss-120b, gpt-oss-20b, gemma-4-31b, and qwen3-8b—using 225 facts that changed after February 16, 2026. The resul

    Matched fieldsTitle

Tuesday