Automatic evaluation with large language models, commonly known as LLM-as-a-judge, is now standard across reasoning and alignment tasks. Despite evaluating many samples in deployment, these evaluators typically (i) treat each case independently, missing the opportunity to accumulate experience, and (ii) rely on a single fixed prompt for all cases, neglecting the need for sample-specific evaluation criteria. We introduce Learning While Evaluating (LWE), a framework that allows evaluators to improve sequentially at inference time without requiring training or validation sets. LWE maintains an evolving meta-prompt that (i) produces sample-specific evaluation instructions and (ii) refines itself through self-generated feedback. Furthermore, we propose Selective LWE, which updates the meta-prompt only on self-inconsistent cases, focusing computation where it matters most. This selective approach retains the benefits of sequential learning while being far more cost-effective. Across two pairwise comparison benchmarks, Selective LWE outperforms strong baselines, empirically demonstrating that evaluators can improve during sequential testing with a simple selective update, learning most from the cases they struggle with.

Designing effective prompts is essential to guiding large language models (LLMs) toward desired responses. Automated prompt engineering aims to reduce reliance on manual effort by streamlining the design, refinement, and optimization of natural language prompts. This paper proposes an optimal learning framework for automated prompt engineering, designed to sequentially identify effective prompt features while efficiently allocating a limited evaluation budget. We introduce a feature-based method to express prompts, which significantly broadens the search space. Bayesian regression is employed to utilize correlations among similar prompts, accelerating the learning process. To efficiently explore the large space of prompt features for a high quality prompt, we adopt the forward-looking Knowledge-Gradient (KG) policy for sequential optimal learning. The KG policy is computed efficiently by solving mixed-integer second-order cone optimization problems, making it scalable and capable of accommodating prompts characterized only through constraints. We demonstrate that our method significantly outperforms a set of benchmark strategies assessed on instruction induction tasks. The results highlight the advantages of using the KG policy for prompt learning given a limited evaluation budget. Our framework provides a solution to deploying automated prompt engineering in a wider range applications where prompt evaluation is costly.

Amid growing concerns over the ease of theft and misuse of Large Language Models (LLMs), the need for fingerprinting models has increased. Fingerprinting, in this context, means that the model owner can link a given model to their original version, thereby identifying if their model is being misused or has been completely stolen. In this paper, we first define a set five properties a successful fingerprint should satisfy; namely, the fingerprint should be Transparent, Efficient, Persistent, Robust, and Unforgeable. Next, we propose Chain & Hash, a new, simple fingerprinting approach that implements a fingerprint with a cryptographic flavor, achieving all these properties. Chain & Hash involves generating a set of questions (the fingerprints) along with a set of potential answers. These elements are hashed together using a secure hashing technique to select the value for each question, hence providing an unforgeability property-preventing adversaries from claiming false ownership. We evaluate the Chain & Hash technique on multiple models and demonstrate its robustness against benign transformations, such as fine-tuning on different datasets, and adversarial attempts to erase the fingerprint. Finally, our experiments demonstrate the efficiency of implementing Chain & Hash and its utility, where fingerprinted models achieve almost the same performance as non-fingerprinted ones across different benchmarks.

When the quality of naive prompts is carefully optimized by human experts, the task performance of large language models (LLMs) can be significantly improved. However, expert-based prompt optimizations are expensive. Herein, some works have proposed Automatic Prompt Optimization (APO), to optimize naive prompts according to task outputs of given in-box testing models, with the help of advanced LLMs (e.g., GPT-4) in an ad-hoc way. Although effective, existing schemes suffer from poor generalization ability and privacy risk. To this end, we collect the first large-scale Prompt Optimization Preference dataset (POP), fine-tune offline local LLM-based optimizers, then fairly test with various downstream models. Our method allows accurate optimization of the core task instruction part within the naive prompt in a model-agnostic manner, and thus is named Free-from Instruction-oriented Prompt Optimization (FIPO). In specific, FIPO uses a modular APO template that dynamically integrate the naive task instruction, optional instruction responses, and optional ground truth to produce finely optimized prompts. The POP dataset is meticulously constructed using advanced LLMs, undergoing rigorous cross-validation by human experts and analytical models. Leveraging insights from the data with Tulu2 models and diverse fine-tuning strategies, we validate the efficacy of FIPO framework across five public benchmarks and three testing models. Check codes and data here: https://github.com/LuJunru/FIPO_Project.

The performance of Large Language Models (LLMs) relies heavily on the quality of prompts, which are often manually engineered and task-specific, making them costly and non-scalable. We propose a novel approach, Supervisory Prompt Training (SPT). SPT automates the generation of highly effective prompts using a dual LLM system. In this system, one LLM, the generator, performs a task while the other, the corrector, provides feedback and generates improved prompts. In contrast to earlier techniques, both the generator and corrector collaboratively and continuously improve their prompts over time. We also introduce the concept of \textit{impact scores} to measure the sentence-level effectiveness of the prompts. Our method was tested on four benchmarks, testing the level of hallucinations in LLMs. Notably, we were able to increase the accuracy of GPT-4 on GSM8K from 65.8\% to 94.1\% (28.3\% increase). SPT advances LLMs by refining prompts to enhance performance and reduce hallucinations, offering an efficient and scalable alternative to traditional model fine-tuning.

Real-world data often have an open long-tailed distribution, and building a unified QA model supporting various tasks is vital for practical QA applications. However, it is non-trivial to extend previous QA approaches since they either require access to seen tasks of adequate samples or do not explicitly model samples from unseen tasks. In this paper, we define Open Long-Tailed QA (OLTQA) as learning from long-tailed distributed data and optimizing performance over seen and unseen QA tasks. We propose an OLTQA model that encourages knowledge sharing between head, tail and unseen tasks, and explicitly mines knowledge from a large pre-trained language model (LM). Specifically, we organize our model through a pool of fine-grained components and dynamically combine these components for an input to facilitate knowledge sharing. A retrieve-then-rerank frame is further introduced to select in-context examples, which guild the LM to generate text that express knowledge for QA tasks. Moreover, a two-stage training approach is introduced to pre-train the framework by knowledge distillation (KD) from the LM and then jointly train the frame and a QA model through an adaptive mutual KD method. On a large-scale OLTQA dataset we curate from 43 existing QA datasets, our model consistently outperforms the state-of-the-art. We release the code and data at \url{https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/oltqa}.

Lifelong learning (LL) is an important ability for NLP models to learn new tasks continuously. Architecture-based approaches are reported to be effective implementations for LL models. However, it is non-trivial to extend previous approaches to domain incremental LL scenarios since they either require access to task identities in the testing phase or cannot handle samples from unseen tasks. In this paper, we propose \textbf{Diana}: a \underline{d}ynam\underline{i}c \underline{a}rchitecture-based lifelo\underline{n}g le\underline{a}rning model that tries to learn a sequence of tasks with a prompt-enhanced language model. Four types of hierarchically organized prompts are used in Diana to capture knowledge from different granularities. Specifically, we dedicate task-level prompts to capture task-specific knowledge to retain high LL performances and maintain instance-level prompts to learn knowledge shared across input samples to improve the model's generalization performance. Moreover, we dedicate separate prompts to explicitly model unseen tasks and introduce a set of prompt key vectors to facilitate knowledge sharing between tasks. Extensive experiments demonstrate that Diana outperforms state-of-the-art LL models, especially in handling unseen tasks. We release the code and data at \url{https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/diana}.

QA models with lifelong learning (LL) abilities are important for practical QA applications, and architecture-based LL methods are reported to be an effective implementation for these models. However, it is non-trivial to extend previous approaches to QA tasks since they either require access to task identities in the testing phase or do not explicitly model samples from unseen tasks. In this paper, we propose Diana: a dynamic architecture-based lifelong QA model that tries to learn a sequence of QA tasks with a prompt enhanced language model. Four types of hierarchically organized prompts are used in Diana to capture QA knowledge from different granularities. Specifically, we dedicate task-level prompts to capture task-specific knowledge to retain high LL performances and maintain instance-level prompts to learn knowledge shared across different input samples to improve the model's generalization performance. Moreover, we dedicate separate prompts to explicitly model unseen tasks and introduce a set of prompt key vectors to facilitate knowledge sharing between tasks. Extensive experiments demonstrate that Diana outperforms state-of-the-art lifelong QA models, especially in handling unseen tasks.