[2402.05119] A Closer Look at the Limitations of Instruction Tuning

Abstract: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.

A Closer Look at the Limitations of Instruction Tuning Sreyan Ghosh * 1 2 Chandra Kiran Reddy Evuru * 1 Sonal Kumar * 1 Ramaneswaran S 3 Deepali Aneja 2 † † Zeyu Jin 2 Ramani Duraiswami 1 Dinesh Manocha 1 Abstract 2023). These models learn general-purpose…

saved by

• Akshith Garapati

related reading

• [2106.09685] LoRA: Low-Rank Adaptation of Large Language Modelsarxiv.org
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
• [2502.17424] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsarxiv.org
• [2203.02155] Training language models to follow instructions with human feedbackarxiv.org
• [2607.14111] Introspection Fine-Tuning (IFT): Training Small LLMs to Introspectarxiv.org
• 2401.10020.pdfarxiv.org
• [2506.17209] Fine-Tuning Lowers Safety and Disrupts Evaluation Consistencyarxiv.org
• 2305.14314arxiv.org
• Large Language Models Must Be Taught to Know What They Don't Knowarxiv.org
• 2308.03958arxiv.org
• Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org