paper-with-me

Papers

Mistral-C2F: Coarse to Fine Actor for Analytical and Reasoning Enhancement in RLHF and Effective-Merged LLMs

2024-06-12 · Chen Zheng, Ke Sun, Xun Zhou

Despite the advances in Large Language Models (LLMs), exemplified by models like GPT-4 and Claude, smaller-scale LLMs such as Llama and Mistral often struggle with generating in-depth and coherent dialogues. This paper presents a novel two-step Coarse-to-Fine Actor model to address the inherent limitations in conversational and analytical capabilities of small-sized LLMs. Our approach begins with the Policy-based Coarse Actor, employing a technique we term "Continuous Maximization". The Coarse Actor establishes an enhanced, knowledge-rich pool adept at aligning with human preference styles in analysis and reasoning. Through the RLHF process, it employs Continuous Maximization, a strategy that dynamically and adaptively extends the output length limit, enabling the generation of more detailed and analytical content. Subsequently, the Fine Actor refines this analytical content, addressing the generation of excessively redundant information from the Coarse Actor. We introduce a "Knowledge Residue Merger" approach, refining the content from the Coarse Actor and merging it with an existing Instruction model to improve quality, correctness, and reduce redundancies. We applied our methodology to the popular Mistral model, creating Mistral-C2F, which has demonstrated exceptional performance across 11 general language tasks and the MT-Bench Dialogue task, outperforming similar-scale models and even larger models with 13B and 30B parameters. Our model has significantly improved conversational and analytical reasoning abilities.

📄 PDF Abstract BibTeX arXiv:2406.08657

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
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…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

CAFE: Retrieval Head-based Coarse-to-Fine Information Seeking to Enhance Multi-Document QA Capability

2025-05-15 · Han Peng, Jinhao Jiang, Zican Dong, Wayne Xin Zhao 외

Advancements in Large Language Models (LLMs) have extended their input context length, yet they still struggle with retrieval and reasoning in long-context inputs. Existing methods propose to utilize the prompt strategy …

Question AnsweringRAGRetrieval

LogReasoner: Empowering LLMs with Expert-like Coarse-to-Fine Reasoning for Automated Log Analysis

2025-09-25 · Lipeng Ma, Yixuan Li, Weidong Yang, Mingjie Zhou 외 arxiv

Log analysis is crucial for monitoring system health and diagnosing failures in complex systems. Recent advances in large language models (LLMs) offer new opportunities for automated log analysis, leveraging their reason…

Anomaly Detection

Mistral 7B

2023-10-10 · Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford 외

We introduce Mistral 7B v0.1, a 7-billion-parameter language model engineered for superior performance and efficiency. Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mat…

answerability predictionArithmetic ReasoningChatbotCode Generation+11

Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports

2025-08-19 · Chengbo Sun, Hui Yi Leong, Lei Li arxiv

The manual creation of the "Impression" section in radiology reports is a primary driver of radiologist burnout. To address this challenge, we propose a coarse-to-fine framework that leverages open-source large language …

Reinforcement Learning

Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models

2026-04-27 · Amogh Sheth, Biruk Assefa, Yi Wen Huang, Andrew Lin 외 arxiv

Large language models (LLMs) excel at multi-step reasoning but incur substantial inference cost. We introduce Causal Attribution Pruning (CAP), a training-free method that identifies critical attention heads by measuring…