Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization

• URL: http://arxiv.org/abs/2412.15453v1
• Date: Thu, 19 Dec 2024 23:22:11 GMT
• Title: Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization
• Authors: Sahil Wadhwa, Chengtian Xu, Haoming Chen, Aakash Mahalingam, Akankshya Kar, Divya Chaudhary,
• Abstract summary: The automatic generation of counter-speech (CS) is a critical strategy for addressing hate speech by providing constructive and informed responses. Existing methods often fail to generate high-quality, impactful, and scalable CS, particularly across diverse linguistic contexts. We propose a novel methodology to enhance CS generation by aligning Large Language Models (LLMs) using Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO)
• Score: 1.1368382184602488
• License:
• Abstract: The automatic generation of counter-speech (CS) is a critical strategy for addressing hate speech by providing constructive and informed responses. However, existing methods often fail to generate high-quality, impactful, and scalable CS, particularly across diverse linguistic contexts. In this paper, we propose a novel methodology to enhance CS generation by aligning Large Language Models (LLMs) using Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO). Our approach leverages DPO to align LLM outputs with human preferences, ensuring contextually appropriate and linguistically adaptable responses. Additionally, we incorporate knowledge grounding to enhance the factual accuracy and relevance of generated CS. Experimental results demonstrate that DPO-aligned models significantly outperform SFT baselines on CS benchmarks while scaling effectively to multiple languages. These findings highlight the potential of preference-based alignment techniques to advance CS generation across varied linguistic settings. The model supervision and alignment is done in English and the same model is used for reporting metrics across other languages like Basque, Italian, and Spanish.

Related papers

• Conditioning LLMs to Generate Code-Switched Text: A Methodology Grounded in Naturally Occurring Data [21.240439045909724]
  Code-switching (CS) is still a critical challenge in Natural Language Processing (NLP) This paper presents a novel methodology to generate CS data using Large Language Models (LLMs) We propose back-translating natural CS sentences into monolingual English, and using the resulting parallel corpus to fine-tune LLMs to turn monolingual sentences into CS.
  arXiv  Detail & Related papers  (2025-02-18T15:04:13Z)
• Lla-VAP: LSTM Ensemble of Llama and VAP for Turn-Taking Prediction [0.0]
  This project expands on existing strategies for turn-taking prediction by employing a multi-modal ensemble approach. We aim to improve the accuracy and efficiency of identifying TRPs in both scripted and unscripted conversational scenarios.
  arXiv  Detail & Related papers  (2024-12-24T00:20:38Z)
• Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback [50.84142264245052]
  This work introduces the Align-SLM framework to enhance the semantic understanding of textless Spoken Language Models (SLMs) Our approach generates multiple speech continuations from a given prompt and uses semantic metrics to create preference data for Direct Preference Optimization (DPO) We evaluate the framework using ZeroSpeech 2021 benchmarks for lexical and syntactic modeling, the spoken version of the StoryCloze dataset for semantic coherence, and other speech generation metrics, including the GPT4-o score and human evaluation.
  arXiv  Detail & Related papers  (2024-11-04T06:07:53Z)
• MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time [50.41806216615488]
  Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora. To make LLMs more usable, aligning them with human preferences is essential. We propose an effective method, textbf MetaAlign, which aims to help LLMs dynamically align with various explicit or implicit preferences specified at inference time.
  arXiv  Detail & Related papers  (2024-10-18T05:31:13Z)
• Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention [71.12193680015622]
  Large Language Models (LLMs) have shown remarkable capabilities in natural language processing. LLMs exhibit significant performance gaps among different languages. We propose Inference-Time Cross-Lingual Intervention (INCLINE) to overcome these limitations without incurring significant costs.
  arXiv  Detail & Related papers  (2024-10-16T11:23:03Z)
• Preference Alignment Improves Language Model-Based TTS [76.70693823683091]
  preference alignment algorithms adjust LMs to align with the preferences of reward models, enhancing the desirability of the generated content. With a 1.15B parameter LM-based TTS model, we demonstrate that preference alignment consistently improves intelligibility, speaker similarity, and proxy subjective evaluation scores.
  arXiv  Detail & Related papers  (2024-09-19T01:58:19Z)
• Unintended Impacts of LLM Alignment on Global Representation [62.6579934112071]
  We show that developers align Large Language Models (LLMs) to user preferences through a variety of procedures, such as Reinforcement Learning From Human Feedback (RLHF) and Direct Preference Optimization (DPO) We explore how alignment impacts performance along three axes of global representation: English dialects, multilingualism, and opinions from and about countries worldwide. We conclude by discussing design decisions that led to these unintended impacts and recommendations for more equitable preference tuning.
  arXiv  Detail & Related papers  (2024-02-22T23:31:22Z)
• 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)
• Integrating Knowledge in End-to-End Automatic Speech Recognition for Mandarin-English Code-Switching [41.88097793717185]
  Code-Switching (CS) is a common linguistic phenomenon in multilingual communities. This paper presents our investigations on end-to-end speech recognition for Mandarin-English CS speech.
  arXiv  Detail & Related papers  (2021-12-19T17:31:15Z)

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.