REVIEW 6 cited by
A Closer Look at the Limitations of Instruction Tuning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 6 Pith papers
-
EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora
EraRAG uses hyperplane-based locality-sensitive hashing to build a hierarchical retrieval graph whose affected regions only are re-summarized when new documents arrive, cutting update cost by up to an order of magnitude.
-
Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning
From Open LLM Leaderboard data grouped by base model, the authors recover a three-factor ordering of LLM capabilities and claim instruction-following causally supports math reasoning.
-
A Knowledge-Injection Framework for Zero-Shot Adaptation of LLMs to Delirium Prediction
Inference-time injection of a GPT-generated clinical risk framework improved zero-shot ICU delirium prediction for LLaMA 8B by 8.6 AUROC points, but the gain depended on report structure and did not appear with a more...
-
Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs
Reasoning LLMs seem better at retrieving hierarchical facts not because they know more but because they navigate better; the key supporting RL experiment is missing from the paper.
-
Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches
Embedding-based QLoRA fine-tuning of causal LLMs matches BERT on single-label patent classification with 10–30x fewer trainable parameters, while instruction-tuning wins on multi-label classification only with ≥100M t...
-
Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
A broad survey of LLM alignment that catalogs objectives, benchmarks, SFT/RLHF/DPO methods, and safety challenges, without contributing new experimental or theoretical results.
Discussion (0). Continue with ORCID to comment.