Preference-based Learning with Retrieval Augmented Generation for Conversational Question Answering

• URL: http://arxiv.org/abs/2503.22303v2
• Date: Tue, 15 Apr 2025 08:10:39 GMT
• Title: Preference-based Learning with Retrieval Augmented Generation for Conversational Question Answering
• Authors: Magdalena Kaiser, Gerhard Weikum,
• Abstract summary: PRAISE is a pipeline-based approach for ConvQA that trains adapters for each of the three subtasks.<n>We show that PRAISE shows improvements per subtask and achieves new state-of-the-art performance on a popular ConvQA benchmark.
• Score: 20.969921246457414
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conversational Question Answering (ConvQA) involves multiple subtasks, i) to understand incomplete questions in their context, ii) to retrieve relevant information, and iii) to generate answers. This work presents PRAISE, a pipeline-based approach for ConvQA that trains LLM adapters for each of the three subtasks. As labeled training data for individual subtasks is unavailable in practice, PRAISE learns from its own generations using the final answering performance as feedback signal without human intervention and treats intermediate information, like relevant evidence, as weakly labeled data. We apply Direct Preference Optimization by contrasting successful and unsuccessful samples for each subtask. In our experiments, we show the effectiveness of this training paradigm: PRAISE shows improvements per subtask and achieves new state-of-the-art performance on a popular ConvQA benchmark, by gaining 15.5 percentage points increase in precision over baselines.

Related papers

• Aligning Instruction Tuning with Pre-training [81.4748965653345]
  We propose Aligning Instruction Tuning with Pre-training (AITP) to align instruction tuning with pre-training distributions.<n>We show consistent performance improvements with AITP on three fully open large language models (LLMs) across eight benchmarks.
  arXiv  Detail & Related papers  (2025-01-16T08:27:40Z)
• Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization [89.04537372465612]
  Socratic pretraining is a question-driven, unsupervised pretraining objective designed to improve controllability in summarization tasks. Our results show that Socratic pretraining cuts task-specific labeled data requirements in half.
  arXiv  Detail & Related papers  (2022-12-20T17:27:10Z)
• Learning To Retrieve Prompts for In-Context Learning [33.176481861880724]
  We propose an efficient method for retrieving prompts for in-context learning using annotated data and a LM. We evaluate our approach on three sequence-to-sequence tasks where language utterances are mapped to meaning representations.
  arXiv  Detail & Related papers  (2021-12-16T05:17:56Z)
• Learning to Ask Conversational Questions by Optimizing Levenshtein Distance [83.53855889592734]
  We introduce a Reinforcement Iterative Sequence Editing (RISE) framework that optimize the minimum Levenshtein distance (MLD) through explicit editing actions. RISE is able to pay attention to tokens that are related to conversational characteristics. Experimental results on two benchmark datasets show that RISE significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-30T08:44:19Z)
• Learning to Rank Question Answer Pairs with Bilateral Contrastive Data Augmentation [39.22166065525888]
  We propose a novel and easy-to-apply data augmentation strategy, namely Bilateral Generation (BiG) With the augmented dataset, we design a contrastive training objective for learning to rank question answer pairs. Experimental results on three benchmark datasets, namely TREC-QA, WikiQA, and ANTIQUE, show that our method significantly improves the performance of ranking models.
  arXiv  Detail & Related papers  (2021-06-21T13:29:43Z)
• Learning Compositional Representation for Few-shot Visual Question Answering [93.4061107793983]
  Current methods of Visual Question Answering perform well on the answers with an amount of training data but have limited accuracy on the novel ones with few examples. We propose to extract the attributes from the answers with enough data, which are later composed to constrain the learning of the few-shot ones. Experimental results on the VQA v2.0 validation dataset demonstrate the effectiveness of our proposed attribute network.
  arXiv  Detail & Related papers  (2021-02-21T10:16:24Z)
• Unshuffling Data for Improved Generalization [65.57124325257409]
  Generalization beyond the training distribution is a core challenge in machine learning. We show that partitioning the data into well-chosen, non-i.i.d. subsets treated as multiple training environments can guide the learning of models with better out-of-distribution generalization.
  arXiv  Detail & Related papers  (2020-02-27T03:07:41Z)
• Improving Multi-Turn Response Selection Models with Complementary Last-Utterance Selection by Instance Weighting [84.9716460244444]
  We consider utilizing the underlying correlation in the data resource itself to derive different kinds of supervision signals. We conduct extensive experiments in two public datasets and obtain significant improvement in both datasets.
  arXiv  Detail & Related papers  (2020-02-18T06:29:01Z)

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.