Improving Instruct Models for Free: A Study on Partial Adaptation

• URL: http://arxiv.org/abs/2504.11626v1
• Date: Tue, 15 Apr 2025 21:35:09 GMT
• Title: Improving Instruct Models for Free: A Study on Partial Adaptation
• Authors: Ozan İrsoy, Pengxiang Cheng, Jennifer L. Chen, Daniel Preoţiuc-Pietro, Shiyue Zhang, Duccio Pappadopulo,
• Abstract summary: We study the performance trajectory between base and instruct models by scaling down the strength of instruction-tuning.<n>We show that, across several model families and model sizes, reducing the strength of instruction-tuning results in material improvement on a few-shot in-context learning benchmark.
• Score: 24.14141732514014
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instruct models, obtained from various instruction tuning or post-training steps, are commonly deemed superior and more usable than their base counterpart. While the model gains instruction following ability, instruction tuning may lead to forgetting the knowledge from pre-training or it may encourage the model being overly conversational or verbose. This, in turn, can lead to degradation of in-context few-shot learning performance. In this work, we study the performance trajectory between base and instruct models by scaling down the strength of instruction-tuning via the partial adaption method. We show that, across several model families and model sizes, reducing the strength of instruction-tuning results in material improvement on a few-shot in-context learning benchmark covering a variety of classic natural language tasks. This comes at the cost of losing some degree of instruction following ability as measured by AlpacaEval. Our study shines light on the potential trade-off between in-context learning and instruction following abilities that is worth considering in practice.

Related papers

• Instruction Tuning for Story Understanding and Generation with Weak Supervision [0.5530212768657544]
  We propose a novel approach called "Weak to Strong Instruction Tuning" for improving story generation. We show that our method significantly enhances performance in story comprehension and generation. Our work shows that adaptive instruction tuning can be a powerful tool in refining generative models for complex narrative tasks.
  arXiv  Detail & Related papers  (2025-01-26T15:59:31Z)
• The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities [51.594836904623534]
  We investigate whether instruction-tuned models possess fundamentally different capabilities from base models that are prompted using in-context examples.<n>We show that the performance of instruction-tuned models is significantly correlated with the in-context performance of their base counterparts.<n>Specifically, we extend this understanding to instruction-tuned models, suggesting that their pretraining data similarly sets a limiting boundary on the tasks they can solve.
  arXiv  Detail & Related papers  (2025-01-15T10:57:55Z)
• Improving Instruction-Following in Language Models through Activation Steering [58.876600545898675]
  We derive instruction-specific vector representations from language models and use them to steer models accordingly.<n>We demonstrate how this method can enhance model adherence to constraints such as output format, length, and word inclusion.<n>Our findings demonstrate that activation steering offers a practical and scalable approach for fine-grained control in language generation.
  arXiv  Detail & Related papers  (2024-10-15T08:38:20Z)
• Revisiting the Superficial Alignment Hypothesis [0.9831489366502302]
  The Superficial Alignment Hypothesis posits that almost all of a language model's abilities and knowledge are learned during pre-training. We re-examine these claims by studying the scaling behavior of post-training with increasing finetuning examples.
  arXiv  Detail & Related papers  (2024-09-27T22:14:10Z)
• An Emulator for Fine-Tuning Large Language Models using Small Language Models [91.02498576056057]
  We introduce emulated fine-tuning (EFT), a principled and practical method for sampling from a distribution that approximates the result of pre-training and fine-tuning at different scales. We show that EFT enables test-time adjustment of competing behavioral traits like helpfulness and harmlessness without additional training. Finally, a special case of emulated fine-tuning, which we call LM up-scaling, avoids resource-intensive fine-tuning of large pre-trained models by ensembling them with small fine-tuned models.
  arXiv  Detail & Related papers  (2023-10-19T17:57:16Z)
• Instruction-following Evaluation through Verbalizer Manipulation [64.73188776428799]
  We propose a novel instruction-following evaluation protocol called verbalizer manipulation. It instructs the model to verbalize the task label with words aligning with model priors to different extents. We observe that the instruction-following abilities of models, across different families and scales, are significantly distinguished by their performance on less natural verbalizers.
  arXiv  Detail & Related papers  (2023-07-20T03:54:24Z)
• In-Context Probing: Toward Building Robust Classifiers via Probing Large Language Models [5.5089506884366735]
  In this paper, we propose an alternative approach, which we term In-Context Probing (ICP) Similar to in-context learning, we contextualize the representation of the input with an instruction, but instead of decoding the output prediction, we probe the contextualized representation to predict the label. We show that ICP performs competitive or superior to finetuning and can be particularly helpful to build classifiers on top of smaller models.
  arXiv  Detail & Related papers  (2023-05-23T15:43:04Z)
• Fairness-guided Few-shot Prompting for Large Language Models [93.05624064699965]
  In-context learning can suffer from high instability due to variations in training examples, example order, and prompt formats. We introduce a metric to evaluate the predictive bias of a fixed prompt against labels or a given attributes. We propose a novel search strategy based on the greedy search to identify the near-optimal prompt for improving the performance of in-context learning.
  arXiv  Detail & Related papers  (2023-03-23T12:28:25Z)
• Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates [52.164757178369804]
  Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the necessary annotation budget. We conduct an empirical study of various Bayesian uncertainty estimation methods and Monte Carlo dropout options for deep pre-trained models in the active learning framework. We also demonstrate that to acquire instances during active learning, a full-size Transformer can be substituted with a distilled version, which yields better computational performance.
  arXiv  Detail & Related papers  (2021-01-20T13:59:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.