Enhanced Detection of Conversational Mental Manipulation Through Advanced Prompting Techniques

• URL: http://arxiv.org/abs/2408.07676v1
• Date: Wed, 14 Aug 2024 17:23:12 GMT
• Title: Enhanced Detection of Conversational Mental Manipulation Through Advanced Prompting Techniques
• Authors: Ivory Yang, Xiaobo Guo, Sean Xie, Soroush Vosoughi,
• Abstract summary: We implement Chain-of-Thought prompting with Zero-Shot and Few-Shot settings on a binary mental manipulation detection task. Our primary objective is to decipher why certain prompting techniques display superior performance.
• Score: 23.710371961866198
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This study presents a comprehensive, long-term project to explore the effectiveness of various prompting techniques in detecting dialogical mental manipulation. We implement Chain-of-Thought prompting with Zero-Shot and Few-Shot settings on a binary mental manipulation detection task, building upon existing work conducted with Zero-Shot and Few- Shot prompting. Our primary objective is to decipher why certain prompting techniques display superior performance, so as to craft a novel framework tailored for detection of mental manipulation. Preliminary findings suggest that advanced prompting techniques may not be suitable for more complex models, if they are not trained through example-based learning.

Related papers

• The Elicitation Game: Evaluating Capability Elicitation Techniques [1.064108398661507]
  We evaluate the effectiveness of capability elicitation techniques by intentionally training model organisms. We introduce a novel method for training model organisms, based on circuit breaking. For a code-generation task, only fine-tuning can elicit the hidden capabilities of our novel model organism.
  arXiv  Detail & Related papers  (2025-02-04T09:54:24Z)
• Advanced Weakly-Supervised Formula Exploration for Neuro-Symbolic Mathematical Reasoning [18.937801725778538]
  We propose an advanced practice for neuro-symbolic reasoning systems to explore the intermediate labels with weak supervision from problem inputs and final outputs. Our experiments on the Mathematics dataset illustrated the effectiveness of our proposals from multiple aspects.
  arXiv  Detail & Related papers  (2025-02-02T02:34:36Z)
• Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning [59.98430756337374]
  Supervised fine-tuning enhances the problem-solving abilities of language models across various mathematical reasoning tasks. Our work introduces a novel technique aimed at cultivating a deeper understanding of the training problems at hand. We propose reflective augmentation, a method that embeds problem reflection into each training instance.
  arXiv  Detail & Related papers  (2024-06-17T19:42:22Z)
• RAG-based Crowdsourcing Task Decomposition via Masked Contrastive Learning with Prompts [21.69333828191263]
  We propose a retrieval-augmented generation-based crowdsourcing framework that reimagines task decomposition (TD) as event detection from the perspective of natural language understanding. We present a Prompt-Based Contrastive learning framework for TD (PBCT), which incorporates a prompt-based trigger detector to overcome dependence. Experiment results demonstrate the competitiveness of our method in both supervised and zero-shot detection.
  arXiv  Detail & Related papers  (2024-06-04T08:34:19Z)
• AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents [58.807802111818994]
  We propose AnySkill, a novel hierarchical method that learns physically plausible interactions following open-vocabulary instructions. Our approach begins by developing a set of atomic actions via a low-level controller trained via imitation learning. An important feature of our method is the use of image-based rewards for the high-level policy, which allows the agent to learn interactions with objects without manual reward engineering.
  arXiv  Detail & Related papers  (2024-03-19T15:41:39Z)
• Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations [60.241144377865716]
  We consider the imitation of sub-optimal demonstrations, with both a small clean demonstration set and a large noisy set. We propose method by evaluating and imitating at the sub-demonstration level, encoding action primitives of varying quality into different skills.
  arXiv  Detail & Related papers  (2023-06-13T17:24:37Z)
• Adversarial Attacks on the Interpretation of Neuron Activation Maximization [70.5472799454224]
  Activation-maximization approaches are used to interpret and analyze trained deep-learning models. In this work, we consider the concept of an adversary manipulating a model for the purpose of deceiving the interpretation.
  arXiv  Detail & Related papers  (2023-06-12T19:54:33Z)
• TEMPERA: Test-Time Prompting via Reinforcement Learning [57.48657629588436]
  We propose Test-time Prompt Editing using Reinforcement learning (TEMPERA) In contrast to prior prompt generation methods, TEMPERA can efficiently leverage prior knowledge. Our method achieves 5.33x on average improvement in sample efficiency when compared to the traditional fine-tuning methods.
  arXiv  Detail & Related papers  (2022-11-21T22:38:20Z)
• Self-supervised Transformer for Deepfake Detection [112.81127845409002]
  Deepfake techniques in real-world scenarios require stronger generalization abilities of face forgery detectors. Inspired by transfer learning, neural networks pre-trained on other large-scale face-related tasks may provide useful features for deepfake detection. In this paper, we propose a self-supervised transformer based audio-visual contrastive learning method.
  arXiv  Detail & Related papers  (2022-03-02T17:44:40Z)
• Towards noise robust trigger-word detection with contrastive learning pre-task for fast on-boarding of new trigger-words [0.0]
  Trigger-word detection plays an important role as the entry point of user's communication with voice assistants. We propose contrastive learning as a pre-training task that helps the detection model to generalize to different words and noise conditions. We show that the contrastive pre-training techniques have comparable results to a traditional classification pre-training on new trigger words with less data availability.
  arXiv  Detail & Related papers  (2021-11-06T22:39:05Z)

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.