Steering Conversational Large Language Models for Long Emotional Support Conversations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929499862466560 |
|---|---|
| author | Madani, Navid Saha, Sougata Srihari, Rohini |
| author_facet | Madani, Navid Saha, Sougata Srihari, Rohini |
| contents | In this study, we address the challenge of enabling large language models (LLMs) to consistently adhere to emotional support strategies in extended conversations. We focus on the steerability of the Llama-2 and Llama-3 suite of models, examining their ability to maintain these strategies throughout interactions. To assess this, we introduce the Strategy Relevant Attention (SRA) metric, which quantifies the model's adherence to the prompted strategy through attention maps. To facilitate our study, we create a strategy-conditioned synthetic conversational dataset derived from the ESConv dataset. We also propose various baselines informed by our proposed SRA metric to address the challenge and propose a fine-tuned model that significantly enhances the steerability of the base model in following the strategy throughout the conversation. The code and data are publicly available on our GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_10453 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Steering Conversational Large Language Models for Long Emotional Support Conversations Madani, Navid Saha, Sougata Srihari, Rohini Computation and Language In this study, we address the challenge of enabling large language models (LLMs) to consistently adhere to emotional support strategies in extended conversations. We focus on the steerability of the Llama-2 and Llama-3 suite of models, examining their ability to maintain these strategies throughout interactions. To assess this, we introduce the Strategy Relevant Attention (SRA) metric, which quantifies the model's adherence to the prompted strategy through attention maps. To facilitate our study, we create a strategy-conditioned synthetic conversational dataset derived from the ESConv dataset. We also propose various baselines informed by our proposed SRA metric to address the challenge and propose a fine-tuned model that significantly enhances the steerability of the base model in following the strategy throughout the conversation. The code and data are publicly available on our GitHub. |
| title | Steering Conversational Large Language Models for Long Emotional Support Conversations |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.10453 |