Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations

• URL: http://arxiv.org/abs/2410.04241v2
• Date: Tue, 29 Oct 2024 17:12:46 GMT
• Title: Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations
• Authors: Sagi Shaier, Ari Kobren, Philip Ogren,
• Abstract summary: We propose the novel task of Question Answering with source citation in ambiguous settings, where multiple valid answers exist. We create a comprehensive framework consisting of: (1) five novel datasets; (2) the first ambiguous multi-hop QA dataset featuring real-world, naturally occurring contexts; and (3) two new metrics to evaluate models' performances. We hope that this new task, datasets, metrics, and baselines will inspire the community to push the boundaries of QA research and develop more trustworthy and interpretable systems.
• Score: 3.3018718917393297
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Resolving knowledge conflicts is a crucial challenge in Question Answering (QA) tasks, as the internet contains numerous conflicting facts and opinions. While some research has made progress in tackling ambiguous settings where multiple valid answers exist, these approaches often neglect to provide source citations, leaving users to evaluate the factuality of each answer. On the other hand, existing work on citation generation has focused on unambiguous settings with single answers, failing to address the complexity of real-world scenarios. Despite the importance of both aspects, no prior research has combined them, leaving a significant gap in the development of QA systems. In this work, we bridge this gap by proposing the novel task of QA with source citation in ambiguous settings, where multiple valid answers exist. To facilitate research in this area, we create a comprehensive framework consisting of: (1) five novel datasets, obtained by augmenting three existing reading comprehension datasets with citation meta-data across various ambiguous settings, such as distractors and paraphrasing; (2) the first ambiguous multi-hop QA dataset featuring real-world, naturally occurring contexts; (3) two new metrics to evaluate models' performances; and (4) several strong baselines using rule-based, prompting, and finetuning approaches over five large language models. We hope that this new task, datasets, metrics, and baselines will inspire the community to push the boundaries of QA research and develop more trustworthy and interpretable systems.

Related papers

• Factuality or Fiction? Benchmarking Modern LLMs on Ambiguous QA with Citations [0.0]
  We evaluate the factual accuracy and citation performance of state-of-the-art large language models (LLMs) on the task of Question Answering (QA) Our results show that larger, recent models consistently predict at least one correct answer in ambiguous contexts but fail to handle cases with multiple valid answers.
  arXiv  Detail & Related papers  (2024-12-23T23:55:19Z)
• Enriching Social Science Research via Survey Item Linking [11.902701975866595]
  We model a task called Survey Item Linking (SIL) in two stages: mention detection and entity disambiguation. To this end, we create a high-quality and richly annotated dataset consisting of 20,454 English and German sentences. We demonstrate that the task is feasible, but observe that errors propagate from the first stage, leading to a lower overall task performance.
  arXiv  Detail & Related papers  (2024-12-20T12:14:33Z)
• Teaching Smaller Language Models To Generalise To Unseen Compositional Questions (Full Thesis) [0.0]
  We train our models to answer diverse questions by instilling an ability to reason over a retrieved context. We acquire context from two knowledge sources; a Wikipedia corpus queried using a multi-hop dense retrieval system with novel extensions, and from rationales generated from a larger Language Model optimised to run in a lower resource environment.
  arXiv  Detail & Related papers  (2024-11-25T23:25:34Z)
• SEMQA: Semi-Extractive Multi-Source Question Answering [94.04430035121136]
  We introduce a new QA task for answering multi-answer questions by summarizing multiple diverse sources in a semi-extractive fashion. We create the first dataset of this kind, QuoteSum, with human-written semi-extractive answers to natural and generated questions.
  arXiv  Detail & Related papers  (2023-11-08T18:46:32Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• Evaluating and Modeling Attribution for Cross-Lingual Question Answering [80.4807682093432]
  This work is the first to study attribution for cross-lingual question answering. We collect data in 5 languages to assess the attribution level of a state-of-the-art cross-lingual QA system. We find that a substantial portion of the answers is not attributable to any retrieved passages.
  arXiv  Detail & Related papers  (2023-05-23T17:57:46Z)
• Dual Semantic Knowledge Composed Multimodal Dialog Systems [114.52730430047589]
  We propose a novel multimodal task-oriented dialog system named MDS-S2. It acquires the context related attribute and relation knowledge from the knowledge base. We also devise a set of latent query variables to distill the semantic information from the composed response representation.
  arXiv  Detail & Related papers  (2023-05-17T06:33:26Z)
• Inquisitive Question Generation for High Level Text Comprehension [60.21497846332531]
  We introduce INQUISITIVE, a dataset of 19K questions that are elicited while a person is reading through a document. We show that readers engage in a series of pragmatic strategies to seek information. We evaluate question generation models based on GPT-2 and show that our model is able to generate reasonable questions.
  arXiv  Detail & Related papers  (2020-10-04T19:03:39Z)
• Knowledgeable Dialogue Reading Comprehension on Key Turns [84.1784903043884]
  Multi-choice machine reading comprehension (MRC) requires models to choose the correct answer from candidate options given a passage and a question. Our research focuses dialogue-based MRC, where the passages are multi-turn dialogues. It suffers from two challenges, the answer selection decision is made without support of latently helpful commonsense, and the multi-turn context may hide considerable irrelevant information.
  arXiv  Detail & Related papers  (2020-04-29T07:04:43Z)

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.