paper-with-me

Papers

A Closer Look at the Limitations of Instruction Tuning

2024-02-03 · Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Ramaneswaran S, Deepali Aneja, Zeyu Jin, Ramani Duraiswami, Dinesh Manocha

Instruction Tuning (IT), the process of training large language models (LLMs) using instruction-response pairs, has emerged as the predominant method for transforming base pre-trained LLMs into open-domain conversational agents. While IT has achieved notable success and widespread adoption, its limitations and shortcomings remain underexplored. In this paper, through rigorous experiments and an in-depth analysis of the changes LLMs undergo through IT, we reveal various limitations of IT. In particular, we show that (1) IT fails to enhance knowledge or skills in LLMs. LoRA fine-tuning is limited to learning response initiation and style tokens, and full-parameter fine-tuning leads to knowledge degradation. (2) Copying response patterns from IT datasets derived from knowledgeable sources leads to a decline in response quality. (3) Full-parameter fine-tuning increases hallucination by inaccurately borrowing tokens from conceptually similar instances in the IT dataset for generating responses. (4) Popular methods to improve IT do not lead to performance improvements over a simple LoRA fine-tuned model. Our findings reveal that responses generated solely from pre-trained knowledge consistently outperform responses by models that learn any form of new knowledge from IT on open-source datasets. We hope the insights and challenges revealed in this paper inspire future work in related directions.

📄 PDF Abstract BibTeX arXiv:2402.05119

Code (0)

등록된 구현이 없습니다.

Tasks

Hallucination

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity

2024-07-22 · Yangzhou Liu, Yue Cao, Zhangwei Gao, Weiyun Wang 외

Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of Vision Large Language Models (VLLMs). However, existing visual instruction tuning datasets include the following limitat…

DiversityMultiple-choiceQuestion AnsweringVisual Question Answering

Do Instruction-Tuned Models Always Perform Better Than Base Models? Evidence from Math and Domain-Shifted Benchmarks

2026-01-19 · Prateek Munjal, Clement Christophe, Ronnie Rajan, Praveenkumar Kanithi arxiv

Instruction finetuning is standard practice for improving LLM performance, yet it remains unclear whether it enhances reasoning or merely induces surface-level pattern matching. We investigate this by evaluating base and…

Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning

2023-10-20 · Duarte M. Alves, Nuno M. Guerreiro, João Alves, José Pombal 외

Large language models (LLMs) are a promising avenue for machine translation (MT). However, current LLM-based MT systems are brittle: their effectiveness highly depends on the choice of few-shot examples and they often re…

In-Context LearningMachine TranslationTranslation

Empowering Reliable Visual-Centric Instruction Following in MLLMs

2026-01-06 · Weilei He, Feng Ju, Zhiyuan Fan, Rui Min 외 arxiv

Evaluating the instruction-following (IF) capabilities of Multimodal Large Language Models (MLLMs) is essential for rigorously assessing how faithfully model outputs adhere to user-specified intentions. Nevertheless, exi…

Instruction Following

Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention

2023-10-29 · Changjiang Gao, ShuJian Huang, Jixing Li, Jiajun Chen

Recent large language models (LLMs) have revealed strong abilities to understand natural language. Since most of them share the same basic structure, i.e. the transformer block, possible contributors to their success in …