Related papers: ASPIRO: Any-shot Structured Parsing-error-Induced …
Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…
Although pretrained language models (PLMs) can be prompted to perform a wide range of language tasks, it remains an open question how much this ability comes from generalizable linguistic understanding versus surface-level lexical patterns.…
Abstractive summarization models are commonly trained using maximum likelihood estimation, which assumes a deterministic (one-point) target distribution in which an ideal model will assign all the probability mass to the reference summary.…
Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of…
Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…
Current methods for prompt learning in zeroshot scenarios widely rely on a development set with sufficient human-annotated data to select the best-performing prompt template a posteriori. This is not ideal because in a realworld zero-shot…
We introduce ASTRO, the "Autoregressive Search-Taught Reasoner", a framework for training language models to reason like search algorithms, explicitly leveraging self-reflection, backtracking, and exploration in their outputs. Recently,…
Language models are achieving impressive performance on various tasks by aggressively adopting inference-time prompting techniques, such as zero-shot and few-shot prompting. In this work, we introduce EchoPrompt, a simple yet effective…
We explore a new language model inversion problem under strict black-box, zero-shot, and limited data conditions. We propose a novel training-free framework that reconstructs prompts using only a limited number of text outputs from a…
Recent prompt-based approaches allow pretrained language models to achieve strong performances on few-shot finetuning by reformulating downstream tasks as a language modeling problem. In this work, we demonstrate that, despite its…
Few-shot or zero-shot fact verification only relies on a few or no labeled training examples. In this paper, we propose a novel method called ProToCo, to \underline{Pro}mpt pre-trained language models (PLMs) \underline{To} be…
Prompt engineering is an iterative procedure often requiring extensive manual effort to formulate suitable instructions for effectively directing large language models (LLMs) in specific tasks. Incorporating few-shot examples is a vital and…
We introduce Bonito, an open-source model for conditional task generation that converts unannotated text into task-specific training datasets for instruction tuning. We aim to enable zero-shot task adaptation of large language models on…
The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have…
While sentence simplification is an active research topic in NLP, its adjacent tasks of sentence complexification and same-level paraphrasing are not. To train models on all three tasks, we present two new unsupervised datasets. We compare…
Does prompting a large language model (LLM) like GPT-3 with explanations improve in-context learning? We study this question on two NLP tasks that involve reasoning over text, namely question answering and natural language inference. We…
Recent research showed promising results on combining pretrained language models (LMs) with canonical utterance for few-shot semantic parsing. The canonical utterance is often lengthy and complex due to the compositional structure of formal…
Large language models (LLMs) have shown remarkable performance in various tasks and have been extensively utilized by the public. However, the increasing concerns regarding the misuse of LLMs, such as plagiarism and spamming, have led to…
In this paper, we propose reverse inference optimization (RIO), a simple and effective method designed to enhance the robustness of autoregressive-model-based zero-shot text-to-speech (TTS) systems using reinforcement learning from human…
Although language models (LMs) have boosted the performance of Question Answering, they still need plenty of data. Data annotation, in contrast, is a time-consuming process. This especially applies to Question Answering, where possibly…