Related papers: ToPro: Token-Level Prompt Decomposition for Cross-…
Multilingual pretrained language models (MPLMs) have demonstrated substantial performance improvements in zero-shot cross-lingual transfer across various natural language understanding tasks by finetuning MPLMs on task-specific labelled…
Deep neural networks have achieved remarkable performance in various text-based tasks but often lack interpretability, making them less suitable for applications where transparency is critical. To address this, we propose ProtoLens, a novel…
Recent studies have demonstrated that natural-language prompts can help to leverage the knowledge learned by pre-trained language models for the binary sentence-level sentiment classification task. Specifically, these methods utilize…
Direct Preference Optimization is an offline post-SFT method for aligning language models from preference pairs, with strong results in instruction following and summarization. However, DPO's sequence-level implicit reward can be brittle…
Recently, prompt-tuning has achieved promising results for specific few-shot classification tasks. The core idea of prompt-tuning is to insert text pieces (i.e., templates) into the input and transform a classification task into a masked…
Video-and-language pre-training has shown promising improvements on various downstream tasks. Most previous methods capture cross-modal interactions with a transformer-based multimodal encoder, not fully addressing the misalignment between…
How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for a wide range of NLP tasks. However, existing approaches…
Prompting method is regarded as one of the crucial progress for few-shot nature language processing. Recent research on prompting moves from discrete tokens based ``hard prompts'' to continuous ``soft prompts'', which employ learnable…
Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…
Large pre-trained vision-language models such as CLIP have demonstrated great potential in zero-shot transferability to downstream tasks. However, to attain optimal performance, the manual selection of prompts is necessary to improve…
We investigate how sentence-level transformers can be modified into effective sequence labelers at the token level without any direct supervision. Existing approaches to zero-shot sequence labeling do not perform well when applied on…
Prompt optimization aims to systematically refine prompts to enhance a language model's performance on specific tasks. Fairness detection in Terms of Service (ToS) clauses is a challenging legal NLP task that demands carefully crafted…
Tokenization serves as a foundational step for Large Language Models (LLMs) to process text. In new domains or languages, the inefficiency of the tokenizer will slow down the training and generation of LLM. The mismatch in vocabulary also…
This work proposes POMP, a prompt pre-training method for vision-language models. Being memory and computation efficient, POMP enables the learned prompt to condense semantic information for a rich set of visual concepts with over…
Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases,…
We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding methods that optimize token-level likelihood rather than sequence-level quality. Our…
In recent years, the use of prompts to guide the output of Large Language Models have increased dramatically. However, even the best of experts struggle to choose the correct words to stitch up a prompt for the desired task. To solve this,…
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.…
Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However,…
Prompt quality plays a central role in controlling the behavior, reliability, and reasoning performance of large language models (LLMs), particularly for smaller open-source instruction-tuned models that depend heavily on explicit…