WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia

• URL: http://arxiv.org/abs/2406.13805v1
• Date: Wed, 19 Jun 2024 20:13:42 GMT
• Title: WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
• Authors: Yufang Hou, Alessandra Pascale, Javier Carnerero-Cano, Tigran Tchrakian, Radu Marinescu, Elizabeth Daly, Inkit Padhi, Prasanna Sattigeri,
• Abstract summary: Retrieval-augmented generation (RAG) has emerged as a promising solution to mitigate the limitations of large language models (LLMs) In this work, we conduct a comprehensive evaluation of LLM-generated answers to questions based on contradictory passages from Wikipedia. We benchmark a diverse range of both closed and open-source LLMs under different QA scenarios, including RAG with a single passage, and RAG with 2 contradictory passages.
• Score: 59.96425443250666
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-augmented generation (RAG) has emerged as a promising solution to mitigate the limitations of large language models (LLMs), such as hallucinations and outdated information. However, it remains unclear how LLMs handle knowledge conflicts arising from different augmented retrieved passages, especially when these passages originate from the same source and have equal trustworthiness. In this work, we conduct a comprehensive evaluation of LLM-generated answers to questions that have varying answers based on contradictory passages from Wikipedia, a dataset widely regarded as a high-quality pre-training resource for most LLMs. Specifically, we introduce WikiContradict, a benchmark consisting of 253 high-quality, human-annotated instances designed to assess LLM performance when augmented with retrieved passages containing real-world knowledge conflicts. We benchmark a diverse range of both closed and open-source LLMs under different QA scenarios, including RAG with a single passage, and RAG with 2 contradictory passages. Through rigorous human evaluations on a subset of WikiContradict instances involving 5 LLMs and over 3,500 judgements, we shed light on the behaviour and limitations of these models. For instance, when provided with two passages containing contradictory facts, all models struggle to generate answers that accurately reflect the conflicting nature of the context, especially for implicit conflicts requiring reasoning. Since human evaluation is costly, we also introduce an automated model that estimates LLM performance using a strong open-source language model, achieving an F-score of 0.8. Using this automated metric, we evaluate more than 1,500 answers from seven LLMs across all WikiContradict instances. To facilitate future work, we release WikiContradict on: https://ibm.biz/wikicontradict.

Related papers

• IdentifyMe: A Challenging Long-Context Mention Resolution Benchmark [22.238377215355545]
  We introduce IdentifyMe, a new benchmark for mention resolution presented in a multiple-choice question (MCQ) format. We observe a significant performance gap between the state-of-the-art sub-10B open models vs. closed ones. The highest-scoring model, GPT-4o, achieves 81.9% accuracy, highlighting the strong referential capabilities of state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2024-11-12T01:05:55Z)
• LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements [59.71218039095155]
  Task of reading comprehension (RC) provides a primary means to assess language models' natural language understanding (NLU) capabilities. If the context aligns with the models' internal knowledge, it is hard to discern whether the models' answers stem from context comprehension or from internal information. To address this issue, we suggest to use RC on imaginary data, based on fictitious facts and entities.
  arXiv  Detail & Related papers  (2024-04-09T13:08:56Z)
• Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? [45.233517779029334]
  We identify whether responses are attributed to generated or retrieved contexts. Experiments reveal a significant bias in several LLMs to favor generated contexts, even when they provide incorrect information.
  arXiv  Detail & Related papers  (2024-01-22T12:54:04Z)
• LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback [65.84061725174269]
  Recent large language models (LLM) are leveraging human feedback to improve their generation quality. We propose LLMRefine, an inference time optimization method to refine LLM's output. We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization. LLMRefine consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.
  arXiv  Detail & Related papers  (2023-11-15T19:52:11Z)
• Fake Alignment: Are LLMs Really Aligned Well? [91.26543768665778]
  This study investigates the substantial discrepancy in performance between multiple-choice questions and open-ended questions. Inspired by research on jailbreak attack patterns, we argue this is caused by mismatched generalization.
  arXiv  Detail & Related papers  (2023-11-10T08:01:23Z)
• BooookScore: A systematic exploration of book-length summarization in the era of LLMs [53.42917858142565]
  We develop an automatic metric, BooookScore, that measures the proportion of sentences in a summary that do not contain any of the identified error types. We find that closed-source LLMs such as GPT-4 and 2 produce summaries with higher BooookScore than those generated by open-source models.
  arXiv  Detail & Related papers  (2023-10-01T20:46:44Z)
• Statistical Knowledge Assessment for Large Language Models [79.07989821512128]
  Given varying prompts regarding a factoid question, can a large language model (LLM) reliably generate factually correct answers? We propose KaRR, a statistical approach to assess factual knowledge for LLMs. Our results reveal that the knowledge in LLMs with the same backbone architecture adheres to the scaling law, while tuning on instruction-following data sometimes compromises the model's capability to generate factually correct text reliably.
  arXiv  Detail & Related papers  (2023-05-17T18:54:37Z)
• LLMMaps -- A Visual Metaphor for Stratified Evaluation of Large Language Models [13.659853119356507]
  Large Language Models (LLMs) have revolutionized natural language processing and demonstrated impressive capabilities in various tasks. They are prone to hallucinations, where the model exposes incorrect or false information in its responses. We propose LLMMaps as a novel visualization technique that enables users to evaluate LLMs' performance with respect to Q&A datasets.
  arXiv  Detail & Related papers  (2023-04-02T05:47:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.