Causal Inference for Human-Language Model Collaboration

• URL: http://arxiv.org/abs/2404.00207v1
• Date: Sat, 30 Mar 2024 01:08:25 GMT
• Title: Causal Inference for Human-Language Model Collaboration
• Authors: Bohan Zhang, Yixin Wang, Paramveer S. Dhillon,
• Abstract summary: We develop CausalCollab, an algorithm designed to estimate the ISE of various interaction strategies in dynamic human-LM collaborations. Our empirical investigations across three distinct human-LM collaboration scenarios reveal that CausalCollab effectively reduces confounding.
• Score: 24.096991077437146
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we examine the collaborative dynamics between humans and language models (LMs), where the interactions typically involve LMs proposing text segments and humans editing or responding to these proposals. Productive engagement with LMs in such scenarios necessitates that humans discern effective text-based interaction strategies, such as editing and response styles, from historical human-LM interactions. This objective is inherently causal, driven by the counterfactual `what-if' question: how would the outcome of collaboration change if humans employed a different text editing/refinement strategy? A key challenge in answering this causal inference question is formulating an appropriate causal estimand: the conventional average treatment effect (ATE) estimand is inapplicable to text-based treatments due to their high dimensionality. To address this concern, we introduce a new causal estimand -- Incremental Stylistic Effect (ISE) -- which characterizes the average impact of infinitesimally shifting a text towards a specific style, such as increasing formality. We establish the conditions for the non-parametric identification of ISE. Building on this, we develop CausalCollab, an algorithm designed to estimate the ISE of various interaction strategies in dynamic human-LM collaborations. Our empirical investigations across three distinct human-LM collaboration scenarios reveal that CausalCollab effectively reduces confounding and significantly improves counterfactual estimation over a set of competitive baselines.

Related papers

• Estimating Causal Effects of Text Interventions Leveraging LLMs [7.2937547395453315]
  This paper proposes a novel approach to estimate causal effects using text transformations facilitated by large language models (LLMs) Unlike existing methods, our approach accommodates arbitrary textual interventions and leverages text-level classifiers with domain adaptation ability to produce robust effect estimates against domain shifts. This flexibility in handling various text interventions is a key advancement in causal estimation for textual data, offering opportunities to better understand human behaviors and develop effective policies within social systems.
  arXiv  Detail & Related papers  (2024-10-28T19:19:35Z)
• Towards Safer Online Spaces: Simulating and Assessing Intervention Strategies for Eating Disorder Discussions [2.752488721131003]
  We present a novel experimental testbed for simulating and assessing intervention strategies in ED-related discussions. Our framework generates synthetic conversations across multiple platforms, models, and ED-related topics. We analyze the impact of various intervention strategies on conversation dynamics across four dimensions.
  arXiv  Detail & Related papers  (2024-09-06T06:27:35Z)
• PersLLM: A Personified Training Approach for Large Language Models [66.16513246245401]
  We propose PersLLM, integrating psychology-grounded principles of personality: social practice, consistency, and dynamic development. We incorporate personality traits directly into the model parameters, enhancing the model's resistance to induction, promoting consistency, and supporting the dynamic evolution of personality.
  arXiv  Detail & Related papers  (2024-07-17T08:13:22Z)
• THOR: Text to Human-Object Interaction Diffusion via Relation Intervention [51.02435289160616]
  We propose a novel Text-guided Human-Object Interaction diffusion model with Relation Intervention (THOR) In each diffusion step, we initiate text-guided human and object motion and then leverage human-object relations to intervene in object motion. We construct Text-BEHAVE, a Text2HOI dataset that seamlessly integrates textual descriptions with the currently largest publicly available 3D HOI dataset.
  arXiv  Detail & Related papers  (2024-03-17T13:17:25Z)
• Large Language Model-based Human-Agent Collaboration for Complex Task Solving [94.3914058341565]
  We introduce the problem of Large Language Models (LLMs)-based human-agent collaboration for complex task-solving. We propose a Reinforcement Learning-based Human-Agent Collaboration method, ReHAC. This approach includes a policy model designed to determine the most opportune stages for human intervention within the task-solving process.
  arXiv  Detail & Related papers  (2024-02-20T11:03:36Z)
• AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents [65.16893197330589]
  Large Language Models (LLMs) have demonstrated their ability to replicate human behaviors across a wide range of scenarios. However, their capability in handling complex, multi-character social interactions has yet to be fully explored. We introduce the Multi-Agent Interaction Evaluation Framework (AntEval), encompassing a novel interaction framework and evaluation methods.
  arXiv  Detail & Related papers  (2024-01-12T11:18:00Z)
• Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection [57.13665112065285]
  Human-Object Interaction (HOI) detection is a challenging computer vision task. We present a framework that enhances HOI detection by incorporating structured text knowledge.
  arXiv  Detail & Related papers  (2023-07-25T14:20:52Z)
• CausalDialogue: Modeling Utterance-level Causality in Conversations [83.03604651485327]
  We have compiled and expanded upon a new dataset called CausalDialogue through crowd-sourcing. This dataset includes multiple cause-effect pairs within a directed acyclic graph (DAG) structure. We propose a causality-enhanced method called Exponential Average Treatment Effect (ExMATE) to enhance the impact of causality at the utterance level in training neural conversation models.
  arXiv  Detail & Related papers  (2022-12-20T18:31:50Z)
• Adaptive Bridge between Training and Inference for Dialogue [36.64781557775641]
  We propose a novel adaptive switching mechanism, which learns to automatically transit between ground-truth learning and generated learning. Our method achieves a significant improvement in terms of metric-based evaluation and human evaluation.
  arXiv  Detail & Related papers  (2021-10-22T02:43:27Z)

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.