Llms for generating and evaluating counterfactuals: A comprehensive study

Turnitin 降AI改写 早检测系统 早降重系统 Turnitin-UK版 万方检测-期刊版 维普编辑部版 Grammarly检测 Paperpass检测 checkpass检测 PaperYY检测
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Counterfactual debating with preset stances for hallucination elimination of llms

Y Fang, M Li, W Wang, H Lin, F Feng - arxiv preprint arxiv:2406.11514, 2024 - arxiv.org
Large Language Models (LLMs) excel in various natural language processing tasks but
struggle with hallucination issues. Existing solutions have considered utilizing LLMs' …
Spara Citera Citerat av 5 Relaterade artiklar Alla 4 versionerna Se som HTML-version
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Counterfactual token generation in large language models

I Chatzi, NC Benz, E Straitouri, S Tsirtsis… - arxiv preprint arxiv …, 2024 - arxiv.org
" Sure, I am happy to generate a story for you: Captain Lyra stood at the helm of her trusty
ship, the Maelstrom's Fury, gazing out at the endless sea.[...] Lyra's eyes welled up with tears …
Spara Citera Citerat av 4 Relaterade artiklar Alla 5 versionerna Se som HTML-version
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

A survey on natural language counterfactual generation

Y Wang, X Qiu, Y Yue, X Guo, Z Zeng, Y Feng… - arxiv preprint arxiv …, 2024 - arxiv.org
Natural language counterfactual generation aims to minimally modify a given text such that
the modified text will be classified into a different class. The generated counterfactuals …
Spara Citera Citerat av 2 Relaterade artiklar Alla 5 versionerna Se som HTML-version
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation

A Bhattacharjee, R Moraffah… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
With the development and proliferation of large, complex, black-box models for solving many
natural language processing (NLP) tasks, there is also an increasing necessity of methods …
Spara Citera Citerat av 1 Relaterade artiklar Alla 3 versionerna
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Reasoning Elicitation in Language Models via Counterfactual Feedback

A Hüyük, X Xu, J Maasch, AV Nori… - arxiv preprint arxiv …, 2024 - arxiv.org
Despite the increasing effectiveness of language models, their reasoning capabilities
remain underdeveloped. In particular, causal reasoning through counterfactual question …
Spara Citera Relaterade artiklar Alla 2 versionerna Se som HTML-version
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation

Q Wang, N Feldhus, S Ostermann… - arxiv preprint arxiv …, 2025 - arxiv.org
Counterfactual examples are widely used in natural language processing (NLP) as valuable
data to improve models, and in explainable artificial intelligence (XAI) to understand model …
Spara Citera Relaterade artiklar Alla 2 versionerna Se som HTML-version