CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity
- URL: http://arxiv.org/abs/2404.10513v1
- Date: Tue, 16 Apr 2024 12:37:10 GMT
- Title: CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity
- Authors: Moshe Berchansky, Daniel Fleischer, Moshe Wasserblat, Peter Izsak,
- Abstract summary: We introduce an attribution-oriented Chain-of-Thought reasoning method to enhance the accuracy of attributions.
Evaluations on two context-enhanced question-answering datasets using GPT-4 demonstrate improved accuracy and correctness of attributions.
- Score: 8.377398103067508
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: State-of-the-art performance in QA tasks is currently achieved by systems employing Large Language Models (LLMs), however these models tend to hallucinate information in their responses. One approach focuses on enhancing the generation process by incorporating attribution from the given input to the output. However, the challenge of identifying appropriate attributions and verifying their accuracy against a source is a complex task that requires significant improvements in assessing such systems. We introduce an attribution-oriented Chain-of-Thought reasoning method to enhance the accuracy of attributions. This approach focuses the reasoning process on generating an attribution-centric output. Evaluations on two context-enhanced question-answering datasets using GPT-4 demonstrate improved accuracy and correctness of attributions. In addition, the combination of our method with finetuning enhances the response and attribution accuracy of two smaller LLMs, showing their potential to outperform GPT-4 in some cases.
Related papers
- Zero-Shot Embeddings Inform Learning and Forgetting with Vision-Language Encoders [6.7181844004432385]
The Inter-Intra Modal Measure (IIMM) functions as a strong predictor of performance changes with fine-tuning.
Fine-tuning on tasks with higher IIMM scores produces greater in-domain performance gains but also induces more severe out-of-domain performance degradation.
With only a single forward pass of the target data, practitioners can leverage this key insight to evaluate the degree to which a model can be expected to improve following fine-tuning.
arXiv Detail & Related papers (2024-07-22T15:35:09Z) - Enhancing Retrieval-Augmented LMs with a Two-stage Consistency Learning Compressor [4.35807211471107]
This work proposes a novel two-stage consistency learning approach for retrieved information compression in retrieval-augmented language models.
The proposed method is empirically validated across multiple datasets, demonstrating notable enhancements in precision and efficiency for question-answering tasks.
arXiv Detail & Related papers (2024-06-04T12:43:23Z) - Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models [102.72940700598055]
In reasoning tasks, even a minor error can cascade into inaccurate results.
We develop a method that avoids introducing external resources, relying instead on perturbations to the input.
Our training approach randomly masks certain tokens within the chain of thought, a technique we found to be particularly effective for reasoning tasks.
arXiv Detail & Related papers (2024-03-04T16:21:54Z) - A Lightweight Parallel Framework for Blind Image Quality Assessment [7.9562077122537875]
We propose a lightweight parallel framework (LPF) for blind image quality assessment (BIQA)
First, we extract the visual features using a pre-trained feature extraction network. Furthermore, we construct a simple yet effective feature embedding network (FEN) to transform the visual features.
We present two novel self-supervised subtasks, including a sample-level category prediction task and a batch-level quality comparison task.
arXiv Detail & Related papers (2024-02-19T10:56:58Z) - Learning to Filter Context for Retrieval-Augmented Generation [75.18946584853316]
Generation models are required to generate outputs given partially or entirely irrelevant passages.
FILCO identifies useful context based on lexical and information-theoretic approaches.
It trains context filtering models that can filter retrieved contexts at test time.
arXiv Detail & Related papers (2023-11-14T18:41:54Z) - Data-Centric Long-Tailed Image Recognition [49.90107582624604]
Long-tail models exhibit a strong demand for high-quality data.
Data-centric approaches aim to enhance both the quantity and quality of data to improve model performance.
There is currently a lack of research into the underlying mechanisms explaining the effectiveness of information augmentation.
arXiv Detail & Related papers (2023-11-03T06:34:37Z) - Towards Reliable and Fluent Large Language Models: Incorporating
Feedback Learning Loops in QA Systems [10.58737969057445]
We build a dataset to train a critic model capable of evaluating the citation, correctness, and fluency of responses generated by large language models.
We propose an automated feedback mechanism that leverages the critic model to offer real-time feedback on heterogeneous aspects of generated text.
Experimental results demonstrate the efficacy of our approach, including a 4% precision increase in citation and an approximately 8% enhancement in the MAUVE metric for fluency.
arXiv Detail & Related papers (2023-09-08T09:39:53Z) - Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection [73.31406286956535]
We introduce the Ladder-of-Thought (LoT) for the stance detection task.
LoT directs the small LMs to assimilate high-quality external knowledge, refining the intermediate rationales produced.
Our empirical evaluations underscore LoT's efficacy, marking a 16% improvement over GPT-3.5 and a 10% enhancement compared to GPT-3.5 with CoT on stance detection task.
arXiv Detail & Related papers (2023-08-31T14:31:48Z) - Adversarial Fine-Tuning of Language Models: An Iterative Optimisation
Approach for the Generation and Detection of Problematic Content [0.0]
We tackle the emerging challenge of unintended harmful content generation in Large Language Models (LLMs)
Our two-pronged approach employs an adversarial model, fine-tuned to generate potentially harmful prompts, and a judge model, iteratively optimised to discern these prompts.
We show that a rudimentary model textttada can achieve 13% higher accuracy on the hold-out test set than GPT-4 after only a few rounds of this process.
arXiv Detail & Related papers (2023-08-26T05:20:58Z) - Tokenization Consistency Matters for Generative Models on Extractive NLP
Tasks [54.306234256074255]
We identify the issue of tokenization inconsistency that is commonly neglected in training generative models.
This issue damages the extractive nature of these tasks after the input and output are tokenized inconsistently.
We show that, with consistent tokenization, the model performs better in both in-domain and out-of-domain datasets.
arXiv Detail & Related papers (2022-12-19T23:33:21Z) - Generating Fact Checking Explanations [52.879658637466605]
A crucial piece of the puzzle that is still missing is to understand how to automate the most elaborate part of the process.
This paper provides the first study of how these explanations can be generated automatically based on available claim context.
Our results indicate that optimising both objectives at the same time, rather than training them separately, improves the performance of a fact checking system.
arXiv Detail & Related papers (2020-04-13T05:23:25Z)
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.