Papers › Elastic Weight Removal for Faithful and Abstractive Dialogue Generation

Elastic Weight Removal for Faithful and Abstractive Dialogue Generation

30 Mar 2023arXiv:2303.17574archive 2025-07-28

Nico Daheim, Nouha Dziri, Mrinmaya Sachan, Iryna Gurevych, Edoardo M. Ponti

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ndaheim/faithful-dialogue officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Dialogue GenerationLanguage ModellingReranking

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdaGradAttentionBPECTRLDense ConnectionsDropoutFlan-T5Gradient ClippingLayer NormalizationLinear LayerLinear WarmupMulti-Head AttentionReLUResidual ConnectionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections