Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF

• URL: http://arxiv.org/abs/2403.10088v1
• Date: Fri, 15 Mar 2024 08:03:49 GMT
• Title: Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF
• Authors: Amey Hengle, Aswini Kumar, Sahajpreet Singh, Anil Bandhakavi, Md Shad Akhtar, Tanmoy Chakroborty,
• Abstract summary: Counterspeech, defined as a response to online hate speech, is increasingly used as a non-censorial solution. Our study introduces CoARL, a novel framework enhancing counterspeech generation by modeling the pragmatic implications underlying social biases in hateful statements. CoARL's first two phases involve sequential multi-instruction tuning, teaching the model to understand intents, reactions, and harms of offensive statements, and then learning task-specific low-rank adapter weights for generating intent-conditioned counterspeech.
• Score: 14.2594830589926
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Counterspeech, defined as a response to mitigate online hate speech, is increasingly used as a non-censorial solution. Addressing hate speech effectively involves dispelling the stereotypes, prejudices, and biases often subtly implied in brief, single-sentence statements or abuses. These implicit expressions challenge language models, especially in seq2seq tasks, as model performance typically excels with longer contexts. Our study introduces CoARL, a novel framework enhancing counterspeech generation by modeling the pragmatic implications underlying social biases in hateful statements. CoARL's first two phases involve sequential multi-instruction tuning, teaching the model to understand intents, reactions, and harms of offensive statements, and then learning task-specific low-rank adapter weights for generating intent-conditioned counterspeech. The final phase uses reinforcement learning to fine-tune outputs for effectiveness and non-toxicity. CoARL outperforms existing benchmarks in intent-conditioned counterspeech generation, showing an average improvement of 3 points in intent-conformity and 4 points in argument-quality metrics. Extensive human evaluation supports CoARL's efficacy in generating superior and more context-appropriate responses compared to existing systems, including prominent LLMs like ChatGPT.

Related papers

• SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks [94.10497337235083]
  We are first to explore the potential of prompting speech LMs in the domain of speech processing. We reformulate speech processing tasks into speech-to-unit generation tasks. We show that the prompting method can achieve competitive performance compared to the strong fine-tuning method.
  arXiv  Detail & Related papers  (2024-08-23T13:00:10Z)
• Outcome-Constrained Large Language Models for Countering Hate Speech [10.434435022492723]
  This study aims to develop methods for generating counterspeech constrained by conversation outcomes. We experiment with large language models (LLMs) to incorporate into the text generation process two desired conversation outcomes. Evaluation results show that our methods effectively steer the generation of counterspeech toward the desired outcomes.
  arXiv  Detail & Related papers  (2024-03-25T19:44:06Z)
• SpeechGPT-Gen: Scaling Chain-of-Information Speech Generation [56.913182262166316]
  Chain-of-Information Generation (CoIG) is a method for decoupling semantic and perceptual information in large-scale speech generation. SpeechGPT-Gen is efficient in semantic and perceptual information modeling. It markedly excels in zero-shot text-to-speech, zero-shot voice conversion, and speech-to-speech dialogue.
  arXiv  Detail & Related papers  (2024-01-24T15:25:01Z)
• Hate Speech Detection via Dual Contrastive Learning [25.878271501274245]
  We propose a novel dual contrastive learning framework for hate speech detection. Our framework jointly optimize the self-supervised and the supervised contrastive learning loss for capturing span-level information. We conduct experiments on two publicly available English datasets, and experimental results show that the proposed model outperforms the state-of-the-art models.
  arXiv  Detail & Related papers  (2023-07-10T13:23:36Z)
• Understanding Counterspeech for Online Harm Mitigation [12.104301755723542]
  Counterspeech offers direct rebuttals to hateful speech by challenging perpetrators of hate and showing support to targets of abuse. It provides a promising alternative to more contentious measures, such as content moderation and deplatforming. This paper systematically reviews counterspeech research in the social sciences and compares methodologies and findings with computer science efforts in automatic counterspeech generation.
  arXiv  Detail & Related papers  (2023-07-01T20:54:01Z)
• Counterspeeches up my sleeve! Intent Distribution Learning and Persistent Fusion for Intent-Conditioned Counterspeech Generation [26.4510688070963]
  In this paper, we explore intent-conditioned counterspeech generation. We develop IntentCONAN, a diversified intent-specific counterspeech dataset with 6831 counterspeeches conditioned on five intents. We propose QUARC, a two-stage framework for intent-conditioned counterspeech generation.
  arXiv  Detail & Related papers  (2023-05-23T07:45:17Z)
• Sentence Representation Learning with Generative Objective rather than Contrastive Objective [86.01683892956144]
  We propose a novel generative self-supervised learning objective based on phrase reconstruction. Our generative learning achieves powerful enough performance improvement and outperforms the current state-of-the-art contrastive methods.
  arXiv  Detail & Related papers  (2022-10-16T07:47:46Z)
• TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation [61.564874831498145]
  TranSpeech is a speech-to-speech translation model with bilateral perturbation. We establish a non-autoregressive S2ST technique, which repeatedly masks and predicts unit choices. TranSpeech shows a significant improvement in inference latency, enabling speedup up to 21.4x than autoregressive technique.
  arXiv  Detail & Related papers  (2022-05-25T06:34:14Z)
• An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks [112.1942546460814]
  We report the first exploration of the prompt tuning paradigm for speech processing tasks based on Generative Spoken Language Model (GSLM) Experiment results show that the prompt tuning technique achieves competitive performance in speech classification tasks with fewer trainable parameters than fine-tuning specialized downstream models.
  arXiv  Detail & Related papers  (2022-03-31T03:26:55Z)
• Characterizing the adversarial vulnerability of speech self-supervised learning [95.03389072594243]
  We make the first attempt to investigate the adversarial vulnerability of such paradigm under the attacks from both zero-knowledge adversaries and limited-knowledge adversaries. The experimental results illustrate that the paradigm proposed by SUPERB is seriously vulnerable to limited-knowledge adversaries.
  arXiv  Detail & Related papers  (2021-11-08T08:44:04Z)
• Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech [9.49544185939481]
  Off-the-shelf Natural Language Generation (NLG) methods are limited in that they generate commonplace, repetitive and safe responses. In this paper, we design a three- module pipeline approach to effectively improve the diversity and relevance. Our proposed pipeline first generates various counterspeech candidates by a generative model to promote diversity, then filters the ungrammatical ones using a BERT model, and finally selects the most relevant counterspeech response.
  arXiv  Detail & Related papers  (2021-06-03T06:54:03Z)

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.