Related papers: Answer-Type Modification without Tears: Prompt-Pas…

Despite the demonstrated empirical efficacy of prompt tuning to adapt a pretrained language model for a new task, the theoretical underpinnings of the difference between "tuning parameters before the input" against "the tuning of model…

The state of the art in machine translation (MT) is governed by neural approaches, which typically provide superior translation accuracy over statistical approaches. However, on the closely related task of word alignment, traditional…

The groundbreaking capabilities of Large Language Models (LLMs) offer new opportunities for enhancing human-computer interaction through emotion-adaptive Artificial Intelligence (AI). However, deliberately controlling the sentiment in these…

Recent advances in pre-trained Vision Language Models (VLM) have shown promising potential for effectively adapting to downstream tasks through prompt learning, without the need for additional annotated paired datasets. To supplement the…

Large language models (LLMs) have become increasingly capable of following instructions and complex reasoning, making prompting a flexible interface for adapting models without parameter updates. Yet prompt design remains labor-intensive…

Although neural machine translation (NMT) models perform well in the general domain, it remains rather challenging to control their generation behavior to satisfy the requirement of different users. Given the expensive training cost and the…

Attribute-based Controlled Text Generation (CTG) refers to generating sentences that satisfy desirable attributes (e.g., emotions and topics). Existing works often utilize fine-tuning or resort to extra attribute classifiers, yet suffer…

Existing memory systems for language agents address memory management: how to retrieve and page more information within a context budget. We address a complementary problem -- memory utility: what experience is worth keeping, and how it…

Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the…

Pre-trained vision-language models (VLMs) have shown remarkable generalization capabilities via prompting, which leverages VLMs as knowledge bases to extract information beneficial for downstream tasks. However, existing methods primarily…

Simultaneous machine translation (SiMT) starts its translation before reading the whole source sentence and employs either fixed or adaptive policy to generate the target sentence. Compared to the fixed policy, the adaptive policy achieves…

Recent Pre-trained Language Models (PLMs) usually only provide users with the inference APIs, namely the emerging Model-as-a-Service (MaaS) setting. To adapt MaaS PLMs to downstream tasks without accessing their parameters and gradients,…

Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…

Type-preserving (or typed) compilation uses typing derivations to certify correctness properties of compilation. We have designed and implemented a type-preserving compiler for a simply-typed dialect of Prolog we call T-Prolog. The crux of…

Pronouns are a long-standing challenge in machine translation. We present a study of the performance of a range of rule-based, statistical and neural MT systems on pronoun translation based on an extensive manual evaluation using the…

Transformer components such as non-linear activations and normalization are inherently non-injective, suggesting that different inputs could map to the same output and prevent exact recovery of the input from a model's representations. In…

Disentangling the content and style in the latent space is prevalent in unpaired text style transfer. However, two major issues exist in most of the current neural models. 1) It is difficult to completely strip the style information from…

Prompt engineering is an increasingly important skill set needed to converse effectively with large language models (LLMs), such as ChatGPT. Prompts are instructions given to an LLM to enforce rules, automate processes, and ensure specific…

Transformer-based NLP models are powerful but have high computational costs that limit deployment. Finetuned encoder-decoder models are popular in specialized domains and can outperform larger more generalized decoder-only models, such as…

We define a notion of normal form bisimilarity for the untyped call-by-value lambda calculus extended with the delimited-control operators shift and reset. Normal form bisimilarities are simple, easy-to-use behavioral equivalences which…