Evaluating Human Alignment and Model Faithfulness of LLM Rationale
- URL: http://arxiv.org/abs/2407.00219v1
- Date: Fri, 28 Jun 2024 20:06:30 GMT
- Title: Evaluating Human Alignment and Model Faithfulness of LLM Rationale
- Authors: Mohsen Fayyaz, Fan Yin, Jiao Sun, Nanyun Peng,
- Abstract summary: We show that prompting-based rationales align better with human-annotated rationales than attribution-based rationales.
We additionally find that the faithfulness limitations of prompting-based methods, which are identified in previous work, may be linked to their collapsed predictions.
- Score: 66.75309523854476
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We study how well large language models (LLMs) explain their generations with rationales -- a set of tokens extracted from the input texts that reflect the decision process of LLMs. We examine LLM rationales extracted with two methods: 1) attribution-based methods that use attention or gradients to locate important tokens, and 2) prompting-based methods that guide LLMs to extract rationales using prompts. Through extensive experiments, we show that prompting-based rationales align better with human-annotated rationales than attribution-based rationales, and demonstrate reasonable alignment with humans even when model performance is poor. We additionally find that the faithfulness limitations of prompting-based methods, which are identified in previous work, may be linked to their collapsed predictions. By fine-tuning these models on the corresponding datasets, both prompting and attribution methods demonstrate improved faithfulness. Our study sheds light on more rigorous and fair evaluations of LLM rationales, especially for prompting-based ones.
Related papers
- Through the Thicket: A Study of Number-Oriented LLMs derived from Random Forest Models [0.0]
Large Language Models (LLMs) have shown exceptional performance in text processing.
This paper proposes a novel approach to training LLMs using knowledge transfer from a random forest (RF) ensemble.
We generate outputs for fine-tuning, enhancing the model's ability to classify and explain its decisions.
arXiv Detail & Related papers (2024-06-07T13:31:51Z) - ReMoDetect: Reward Models Recognize Aligned LLM's Generations [55.06804460642062]
Large language models (LLMs) generate human-preferable texts.
We propose two training schemes to further improve the detection ability of the reward model.
arXiv Detail & Related papers (2024-05-27T17:38:33Z) - A Causal Explainable Guardrails for Large Language Models [29.441292837667415]
Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases.
Existing methods for steering LLMs towards desired attributes often assume unbiased representations and rely solely on steering prompts.
We propose LLMGuardaril, a novel framework that incorporates causal analysis and adversarial learning to obtain unbiased steering representations.
arXiv Detail & Related papers (2024-05-07T09:55:05Z) - Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment [32.12998469814097]
A novel causal prompting method based on front-door adjustment is proposed to effectively mitigate Large Language Models (LLMs) biases.
Experimental results show that the proposed causal prompting approach achieves excellent performance across seven natural language processing datasets.
arXiv Detail & Related papers (2024-03-05T07:47:34Z) - Learning to Generate Explainable Stock Predictions using Self-Reflective
Large Language Models [54.21695754082441]
We propose a framework to teach Large Language Models (LLMs) to generate explainable stock predictions.
A reflective agent learns how to explain past stock movements through self-reasoning, while the PPO trainer trains the model to generate the most likely explanations.
Our framework can outperform both traditional deep-learning and LLM methods in prediction accuracy and Matthews correlation coefficient.
arXiv Detail & Related papers (2024-02-06T03:18:58Z) - LLMs for Relational Reasoning: How Far are We? [8.840750655261251]
Large language models (LLMs) have revolutionized many areas by achieving state-of-the-art performance on downstream tasks.
Recent efforts have demonstrated that the LLMs are poor at solving sequential decision-making problems.
arXiv Detail & Related papers (2024-01-17T08:22:52Z) - Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models [56.34029644009297]
Large language models (LLMs) have demonstrated the ability to overcome various limitations of formal Knowledge Representation (KR) systems.
LLMs excel most in abductive reasoning, followed by deductive reasoning, while they are least effective at inductive reasoning.
We study single-task training, multi-task training, and "chain-of-thought" knowledge distillation fine-tuning technique to assess the performance of model.
arXiv Detail & Related papers (2023-10-02T01:00:50Z) - Faithful Explanations of Black-box NLP Models Using LLM-generated
Counterfactuals [67.64770842323966]
Causal explanations of predictions of NLP systems are essential to ensure safety and establish trust.
Existing methods often fall short of explaining model predictions effectively or efficiently.
We propose two approaches for counterfactual (CF) approximation.
arXiv Detail & Related papers (2023-10-01T07:31:04Z) - On Learning to Summarize with Large Language Models as References [101.79795027550959]
Large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets.
We study an LLM-as-reference learning setting for smaller text summarization models to investigate whether their performance can be substantially improved.
arXiv Detail & Related papers (2023-05-23T16:56:04Z)
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.