While large-scale neural language models, such as GPT2 and BART,have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-level loops with maximization-based decoding algorithms (\textit{e.g.}, greedy search). This phenomenon is counter-intuitive since there are few consecutive sentence-level repetitions in the human corpus (e.g., 0.02\% in Wikitext-103). To investigate the underlying reasons for generating consecutive sentence-level repetitions, we study the relationship between the probability of repetitive tokens and their previous repetitions in context. Through our quantitative experiments, we find that 1) Models have a preference to repeat the previous sentence; 2) The sentence-level repetitions have a \textit{self-reinforcement effect}: the more times a sentence is repeated in the context, the higher the probability of continuing to generate that sentence; 3) The sentences with higher initial probabilities usually have a stronger self-reinforcement effect. Motivated by our findings, we propose a simple and effective training method \textbf{DITTO} (Pseu\underline{D}o-Repet\underline{IT}ion Penaliza\underline{T}i\underline{O}n), where the model learns to penalize probabilities of sentence-level repetitions from synthetic repetitive data. Although our method is motivated by mitigating repetitions, our experiments show that DITTO not only mitigates the repetition issue without sacrificing perplexity, but also achieves better generation quality. Extensive experiments on open-ended text generation (Wikitext-103) and text summarization (CNN/DailyMail) demonstrate the generality and effectiveness of our method.

We calculate it for each sequence x and average over the whole corpus. When decoding auto-regressively, the probabilities of the repetitive sentence loops also have a self-reinforcement effect. As shown in Figure 2, the probability of the token'located' increases almost The work was conducted in Apple. Here we use the end token to split sentences for ease of experiments. We present the probability of the token'located' ( y-axis) as the number of historical repetitions Best viewed in color and zoomed in a desktop monitor.

Trip recommendation has emerged as a highly sought-after service over the past decade. Although current studies significantly understand human intention consistency, they struggle with undesired repetitive outcomes that need resolution. We make two pivotal discoveries using statistical analyses and experimental designs: (1) The occurrence of repetitions is intricately linked to the models and decoding strategies. (2) During training and decoding, adding perturbations to logits can reduce repetition. Motivated by these observations, we introduce AR-Trip (Anti Repetition for Trip Recommendation), which incorporates a cycle-aware predictor comprising three mechanisms to avoid duplicate Points-of-Interest (POIs) and demonstrates their effectiveness in alleviating repetition. Experiments on four public datasets illustrate that AR-Trip successfully mitigates repetition issues while enhancing precision.

While large-scale neural language models, such as GPT2 and BART,have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-level loops with maximization-based decoding algorithms (\textit{e.g.}, greedy search). This phenomenon is counter-intuitive since there are few consecutive sentence-level repetitions in the human corpus (e.g., 0.02\% in Wikitext-103). To investigate the underlying reasons for generating consecutive sentence-level repetitions, we study the relationship between the probability of repetitive tokens and their previous repetitions in context. Through our quantitative experiments, we find that 1) Models have a preference to repeat the previous sentence; 2) The sentence-level repetitions have a \textit{self-reinforcement effect}: the more times a sentence is repeated in the context, the higher the probability of continuing to generate that sentence; 3) The sentences with higher initial probabilities usually have a stronger self-reinforcement effect. Motivated by our findings, we propose a simple and effective training method \textbf{DITTO} (Pseu\underline{D}o-Repet\underline{IT}ion Penaliza\underline{T}i\underline{O}n), where the model learns to penalize probabilities of sentence-level repetitions from synthetic repetitive data.