Elastic Weight Removal for Faithful and Abstractive Dialogue Generation

• URL: http://arxiv.org/abs/2303.17574v1
• Date: Thu, 30 Mar 2023 17:40:30 GMT
• Title: Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
• Authors: Nico Daheim, Nouha Dziri, Mrinmaya Sachan, Iryna Gurevych, Edoardo M. Ponti
• Abstract summary: A dialogue system should generate responses that are faithful to the knowledge contained in relevant documents. Many models generate hallucinated responses instead that contradict it or contain unverifiable information. We show that our method can be extended to simultaneously discourage hallucinations and extractive responses.
• Score: 61.40951756070646
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ideally, dialogue systems should generate responses that are faithful to the knowledge contained in relevant documents. However, many models generate hallucinated responses instead that contradict it or contain unverifiable information. To mitigate such undesirable behaviour, it has been proposed to fine-tune a `negative expert' on negative examples and subtract its parameters from those of a pre-trained model. However, intuitively, this does not take into account that some parameters are more responsible than others in causing hallucinations. Thus, we propose to weigh their individual importance via (an approximation of) the Fisher Information matrix, which measures the uncertainty of their estimate. We call this method Elastic Weight Removal (EWR). We evaluate our method -- using different variants of Flan-T5 as a backbone language model -- on multiple datasets for information-seeking dialogue generation and compare our method with state-of-the-art techniques for faithfulness, such as CTRL, Quark, DExperts, and Noisy Channel reranking. Extensive automatic and human evaluation shows that EWR systematically increases faithfulness at minor costs in terms of other metrics. However, we notice that only discouraging hallucinations may increase extractiveness, i.e. shallow copy-pasting of document spans, which can be undesirable. Hence, as a second main contribution, we show that our method can be extended to simultaneously discourage hallucinations and extractive responses. We publicly release the code for reproducing EWR and all baselines.

Related papers

• F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI [15.314388210699443]
  Fine-tuned Fidelity F-Fidelity is a robust evaluation framework for XAI. We show that F-Fidelity significantly improves upon prior evaluation metrics in recovering the ground-truth ranking of explainers. We also show that given a faithful explainer, F-Fidelity metric can be used to compute the sparsity of influential input components.
  arXiv  Detail & Related papers  (2024-10-03T20:23:06Z)
• Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment [84.32768080422349]
  Alignment with human preference prevents large language models from generating misleading or toxic content. We propose a new formulation of prompt diversity, implying a linear correlation with the final performance of LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2024-03-17T07:08:55Z)
• Cobra Effect in Reference-Free Image Captioning Metrics [58.438648377314436]
  A proliferation of reference-free methods, leveraging visual-language pre-trained models (VLMs), has emerged. In this paper, we study if there are any deficiencies in reference-free metrics. We employ GPT-4V as an evaluative tool to assess generated sentences and the result reveals that our approach achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2024-02-18T12:36:23Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• Mutual Wasserstein Discrepancy Minimization for Sequential Recommendation [82.0801585843835]
  We propose a novel self-supervised learning framework based on Mutual WasserStein discrepancy minimization MStein for the sequential recommendation. We also propose a novel contrastive learning loss based on Wasserstein Discrepancy Measurement.
  arXiv  Detail & Related papers  (2023-01-28T13:38:48Z)
• Diving Deep into Modes of Fact Hallucinations in Dialogue Systems [2.8360662552057323]
  Knowledge Graph(KG) grounded conversations often use large pre-trained models and usually suffer from fact hallucination. We build an entity-level hallucination detection system, which would provide fine-grained signals that control fallacious content while generating responses.
  arXiv  Detail & Related papers  (2023-01-11T13:08:57Z)
• DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations [46.942369532632604]
  We propose a Dialogue Evaluation metric that relies on AMR-based semantic manipulations for incoherent data generation. Our experiments show that DEAM achieves higher correlations with human judgments compared to baseline methods.
  arXiv  Detail & Related papers  (2022-03-18T03:11:35Z)
• FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization [34.2456005415483]
  We tackle the problem of evaluating faithfulness of a generated summary given its source document. We find that current models exhibit a trade-off between abstractiveness and faithfulness. We propose an automatic question answering (QA) based metric for faithfulness.
  arXiv  Detail & Related papers  (2020-05-07T21:00:08Z)

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.