paper-with-me

홈 › Papers

CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity

2024-04-16 · Moshe Berchansky, Daniel Fleischer, Moshe Wasserblat, Peter Izsak

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.

📄 PDF Abstract BibTeX arXiv:2404.10513

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Local Causal Attribution of Chain-of-Thought Reasoning

2026-06-20 · Dennis Wei, Yannis Belkhiter, Erik Miehling, Radu Marinescu arxiv

Understanding the causal structure of a language model's thought process is a problem of significant importance for both transparency and safety. In this work, we take a local approach toward this goal by analyzing the c…

What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT Reasoning

2025-11-19 · Jeremias Ferrao, Ezgi Basar, Khondoker Ittehadul Islam, Mahrokh Hassani arxiv

This study investigates the attribution patterns underlying Chain-of-Thought (CoT) reasoning in multilingual LLMs. While prior works demonstrate the role of CoT prompting in improving task performance, there are concerns…

A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains

2024-02-01 · Alon Jacovi, Yonatan Bitton, Bernd Bohnet, Jonathan Herzig 외

Prompting language models to provide step-by-step answers (e.g., "Chain-of-Thought") is the prominent approach for complex reasoning tasks, where more accurate reasoning chains typically improve downstream task performan…

Open-Domain Question AnsweringQuestion Answering

Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics

2025-08-29 · Sheldon Yu, Yuxin Xiong, Junda Wu, Xintong Li 외 arxiv

Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains limited, with prior work primarily focu…

Towards Faithful Chain-of-Thought: Large Language Models are Bridging Reasoners

2024-05-29 · Jiachun Li, Pengfei Cao, Yubo Chen, Kang Liu 외

Large language models (LLMs) suffer from serious unfaithful chain-of-thought (CoT) issues. Previous work attempts to measure and explain it but lacks in-depth analysis within CoTs and does not consider the interactions a…