paper-with-me

홈 › Papers

Can Language Models Take A Hint? Prompting for Controllable Contextualized Commonsense Inference

2024-10-03 · Pedro Colon-Hernandez, Nanxi Liu, Chelsea Joe, Peter Chin, Claire Yin, Henry Lieberman, Yida Xin, Cynthia Breazeal

Generating commonsense assertions within a given story context remains a difficult task for modern language models. Previous research has addressed this problem by aligning commonsense inferences with stories and training language generation models accordingly. One of the challenges is determining which topic or entity in the story should be the focus of an inferred assertion. Prior approaches lack the ability to control specific aspects of the generated assertions. In this work, we introduce "hinting," a data augmentation technique that enhances contextualized commonsense inference. "Hinting" employs a prefix prompting strategy using both hard and soft prompts to guide the inference process. To demonstrate its effectiveness, we apply "hinting" to two contextual commonsense inference datasets: ParaCOMET and GLUCOSE, evaluating its impact on both general and context-specific inference. Furthermore, we evaluate "hinting" by incorporating synonyms and antonyms into the hints. Our results show that "hinting" does not compromise the performance of contextual commonsense inference while offering improved controllability.

📄 PDF Abstract BibTeX arXiv:2410.02202

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationText Generation

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Can Language Models Take A Hint? Prompting for Controllable Contextualized Commonsense Inference

2021-10-16 · ACL ARR October 2021 10 · Anonymous

Generating commonsense assertions, given a certain story context, is a tough challenge even for modern language models. One of the reasons for this may be that the model has to "guess" what topic or entity in a story to …

Data AugmentationText Generation

Give me a hint: Can LLMs take a hint to solve math problems?

2024-10-08 · Vansh Agrawal, Pratham Singla, Amitoj Singh Miglani, Shivank Garg 외

While state-of-the-art LLMs have shown poor logical and basic mathematical reasoning, recent works try to improve their problem-solving abilities using prompting techniques. We propose giving "hints" to improve the langu…

Adversarial RobustnessMathMathematical ReasoningSensitivity

Adversarial Transformer Language Models for Contextual Commonsense Inference

2023-02-10 · Pedro Colon-Hernandez, Henry Lieberman, Yida Xin, Claire Yin 외

Contextualized or discourse aware commonsense inference is the task of generating coherent commonsense assertions (i.e., facts) from a given story, and a particular sentence from that story. Some problems with the task a…

Knowledge GraphsLanguage ModelingLanguage ModellingSentence

HINT: Composed Image Retrieval with Dual-path Compositional Contextualized Network

2026-03-27 · Mingyu Zhang, Zixu Li, Zhiwei Chen, Zhiheng Fu 외 arxiv

Composed Image Retrieval (CIR) is a challenging image retrieval paradigm. It aims to retrieve target images from large-scale image databases that are consistent with the modification semantics, based on a multimodal quer…

Image Retrieval

Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights

2024-07-16 · Shunqi Mao, Chaoyi Zhang, Hang Su, Hwanjun Song 외

Contextualized Image Captioning (CIC) evolves traditional image captioning into a more complex domain, necessitating the ability for multimodal reasoning. It aims to generate image captions given specific contextual info…

Image CaptioningMultimodal Reasoning