Emotional support conversation systems are designed to alleviate users’ emotional distress and assist them in overcoming their challenges. While previous studies have made progress, their models occasionally generate unhelpful responses, which are intended to be supportive but instead have counterproductive effects. Since unhelpful responses can hinder the effectiveness of emotional support, it is crucial to mitigate them within conversations. Our solution is motivated by two principal considerations: (1) multiple facets of emotional support are expected to be considered when developing emotional support conversation models, and (2) directly reducing the probability of generating unhelpful responses can effectively mitigate their occurrence. Accordingly, we introduce a novel model-agnostic framework named  ̲Mitigating  ̲unhelpfulness with multifaceted AI  ̲feedback for emot ̲io ̲nal support (Muffin). It first employs a multifaceted AI feedback module designed to assess the helpfulness model responses across various facets of emotional support. Leveraging contrastive learning, Muffin then reduces the unhelpful responses’ likelihoods. To validate the effectiveness of our proposed framework, we apply Muffin to various previous emotional support generation models, including the state-of-the-art. Experimental results demonstrate that Muffin can significantly mitigate unhelpful response generation while enhancing response fluency and relevance.

Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. Yet, traditional tuning narrowly views dialogue generation as resembling other language generation tasks, ignoring the role disparities between two speakers and the multi-round interactive process that dialogues ought to be. Such a manner often leads to unsatisfactory chat consistency for the built agent. In this work, we emphasize the interactive, communicative nature of dialogue and argue that it is more feasible to model the speaker roles of agent and user separately, enabling the agent to adhere to its role consistently. With this in mind, we propose an efficient Multi-round Interactive Dialogue Tuning (Midi-Tuning) framework. It models the agent and user individually with two adapters built upon large language models. The adapters make use of respective utterances round by round in alternating order and they are tuned via a round-level memory caching mechanism. Extensive experiments demonstrate that, our framework performs superior to traditional fine-tuning and harbors the tremendous potential for improving dialogue consistency.

Language model detoxification aims to minimize the risk of generating offensive or harmful content in pretrained language models (PLMs) for safer deployment. Existing methods can be roughly categorized as finetuning-based and decoding-based. However, the former is often resource-intensive, while the latter relies on additional components and potentially compromises the generation fluency. In this paper, we propose a more lightweight approach that enables the PLM itself to achieve “self-detoxification”. Our method is built upon the observation that prepending a negative steering prompt can effectively induce PLMs to generate toxic content. At the same time, we are inspired by the recent research in the interpretability field, which formulates the evolving contextualized representations within the PLM as an information stream facilitated by the attention layers. Drawing on this idea, we devise a method to identify the toxification direction from the normal generation process to the one prompted with the negative prefix, and then steer the generation to the reversed direction by manipulating the information movement within the attention layers. Experimental results show that our approach, without any fine-tuning or extra components, can achieve comparable performance with state-of-the-art methods.