Tuning-Free Personalized Alignment via Trial-Error-Explain In-Context Learning

• URL: http://arxiv.org/abs/2502.08972v1
• Date: Thu, 13 Feb 2025 05:20:21 GMT
• Title: Tuning-Free Personalized Alignment via Trial-Error-Explain In-Context Learning
• Authors: Hyundong Cho, Karishma Sharma, Nicolaas Jedema, Leonardo F. R. Ribeiro, Alessandro Moschitti, Ravi Krishnan, Jonathan May,
• Abstract summary: We present Trial-Error-Explain In-Context Learning (TICL), a tuning-free method that personalizes language models for text generation tasks. TICL iteratively expands an in-context learning prompt via a trial-error-explain process, adding model-generated negative samples and explanations. TICL achieves up to 91.5% against the previous state-of-the-art and outperforms competitive tuning-free baselines for personalized alignment tasks.
• Score: 74.56097953187994
• License:
• Abstract: Language models are aligned to the collective voice of many, resulting in generic outputs that do not align with specific users' styles. In this work, we present Trial-Error-Explain In-Context Learning (TICL), a tuning-free method that personalizes language models for text generation tasks with fewer than 10 examples per user. TICL iteratively expands an in-context learning prompt via a trial-error-explain process, adding model-generated negative samples and explanations that provide fine-grained guidance towards a specific user's style. TICL achieves favorable win rates on pairwise comparisons with LLM-as-a-judge up to 91.5% against the previous state-of-the-art and outperforms competitive tuning-free baselines for personalized alignment tasks of writing emails, essays and news articles. Both lexical and qualitative analyses show that the negative samples and explanations enable language models to learn stylistic context more effectively and overcome the bias towards structural and formal phrases observed in their zero-shot outputs. By front-loading inference compute to create a user-specific in-context learning prompt that does not require extra generation steps at test time, TICL presents a novel yet simple approach for personalized alignment.

Related papers

• On the Loss of Context-awareness in General Instruction Fine-tuning [101.03941308894191]
  We investigate the loss of context awareness after supervised fine-tuning. We find that the performance decline is associated with a bias toward different roles learned during conversational instruction fine-tuning. We propose a metric to identify context-dependent examples from general instruction fine-tuning datasets.
  arXiv  Detail & Related papers  (2024-11-05T00:16:01Z)
• Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods [69.36397993451742]
  This work introduces Context-aware Prompt Tuning (CPT), a method inspired by ICL, PT, and adversarial attacks. We modify specific context tokens, considering the unique structure of input and output formats. Inspired by adversarial attacks, we adjust the input based on the labels present in the context, focusing on minimizing, rather than maximizing, the loss.
  arXiv  Detail & Related papers  (2024-10-22T17:45:47Z)
• Show, Don't Tell: Aligning Language Models with Demonstrated Feedback [54.10302745921713]
  Demonstration ITerated Task Optimization (DITTO) directly aligns language model outputs to a user's demonstrated behaviors. We evaluate DITTO's ability to learn fine-grained style and task alignment across domains such as news articles, emails, and blog posts.
  arXiv  Detail & Related papers  (2024-06-02T23:13:56Z)
• Discourse-Aware In-Context Learning for Temporal Expression Normalization [7.621550020607368]
  In this work, we explore the feasibility of proprietary and open-source large language models (LLMs) for TE normalization. By using a window-based prompt design approach, we can perform TE normalization across sentences, while leveraging the LLM knowledge without training the model. Our experiments show competitive results to models designed for this task.
  arXiv  Detail & Related papers  (2024-04-11T14:13:44Z)
• In-context Prompt Learning for Test-time Vision Recognition with Frozen Vision-language Model [13.983810804606264]
  We propose In-Context Prompt Learning (InCPL) for test-time visual recognition tasks. InCPL associates a new test sample with very few labeled examples as context information. We introduce a context-aware unsupervised loss to optimize visual prompts tailored to test samples.
  arXiv  Detail & Related papers  (2024-03-10T08:15:51Z)
• Instruction Position Matters in Sequence Generation with Large Language Models [67.87516654892343]
  Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization. We propose enhancing the instruction-following capability of LLMs by shifting the position of task instructions after the input sentences.
  arXiv  Detail & Related papers  (2023-08-23T12:36:57Z)
• Zero-Shot Text Classification via Self-Supervised Tuning [46.9902502503747]
  We propose a new paradigm based on self-supervised learning to solve zero-shot text classification tasks. tuning the language models with unlabeled data, called self-supervised tuning. Our model outperforms the state-of-the-art baselines on 7 out of 10 tasks.
  arXiv  Detail & Related papers  (2023-05-19T05:47:33Z)
• Compositional Exemplars for In-context Learning [21.961094715261133]
  Large pretrained language models (LMs) have shown impressive In-Context Learning (ICL) ability. We propose CEIL (Compositional Exemplars for In-context Learning) to model the interaction between the given input and in-context examples. We validate CEIL on 12 classification and generation datasets from 7 distinct NLP tasks, including sentiment analysis, paraphrase detection, natural language inference, commonsense reasoning, open-domain question answering, code generation, and semantic parsing.
  arXiv  Detail & Related papers  (2023-02-11T14:02:08Z)

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.