Consider this prompt "Draw a unicorn with two horns". Should large language models (LLMs) recognize that a unicorn has only one horn by definition and ask users for clarifications, or proceed to generate something anyway? We introduce *concept incongruence* to capture such phenomena where concept boundaries clash with each other, either in user prompts or in model representations, often leading to under-specified or mis-specified behaviors. In this work, we take the first step towards defining and analyzing model behavior under concept incongruence. Focusing on temporal boundaries in the Role-Play setting, we propose three behavioral metrics---abstention rate, conditional accuracy, and answer rate---to quantify model behavior under incongruence due to the role's death. We show that models fail to abstain after death and suffer from an accuracy drop compared to the Non-Role-Play setting. Through probing experiments, we identify two main causes: (i) unreliable encoding of the "death" state across different years, leading to unsatisfactory abstention behavior, and (ii) role playing causes shifts in the model’s temporal representations, resulting in accuracy drops. We leverage these insights to improve consistency in the model's abstention and answer behaviors. Our findings suggest that concept incongruence leads to unexpected model behaviors and point to future directions on improving model behavior under concept incongruence.

While alignment algorithms are commonly used to tune pre-trained language models towards user preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it difficult to explain phenomena like jailbreaks. In this work we study a popular algorithm, direct preference optimization (DPO), and the mechanisms by which it reduces toxicity. Namely, we first study how toxicity is represented and elicited in pre-trained language models (GPT2-medium, Llama2-7b). We then apply DPO with a carefully crafted pairwise dataset to reduce toxicity. We examine how the resulting models avert toxic outputs, and find that capabilities learned from pre-training are not removed, but rather bypassed. We use this insight to demonstrate a simple method to un-align the models, reverting them back to their toxic behavior.

Large Language Models (LLMs) have achieved remarkable success with their billion-level parameters, yet they incur high inference overheads. The emergence of activation sparsity in LLMs provides a natural approach to reduce this cost by involving only parts of the parameters for inference. However, existing methods only focus on utilizing this naturally formed activation sparsity in a post-training setting, overlooking the potential for further amplifying this inherent sparsity. In this paper, we hypothesize that LLMs can learn to be efficient by achieving more structured activation sparsity. To achieve this, we introduce a novel training algorithm, Learn-To-be-Efficient (LTE), designed to train efficiency-aware LLMs to learn to activate fewer neurons and achieve a better trade-off between sparsity and performance. Furthermore, unlike SOTA MoEfication methods, which mainly focus on ReLU-based models, LTE can also be applied to LLMs like LLaMA using non-ReLU activations. Extensive evaluation on language understanding, language generation, and instruction tuning tasks show that LTE consistently outperforms SOTA baselines. Along with our hardware-aware custom kernel implementation, LTE reduces LLaMA2-7B inference latency by 25% at 50% sparsity.

The keyphrase extraction task refers to the automatic selection of phrases from a given document to summarize its core content.Stateof-the-art (SOTA) performance has recently been achieved by embedding-based algorithms, which rank candidates according to how similar their embeddings are to document embeddings.However, such solutions either struggle with the document and candidate length discrepancies or fail to fully utilize the pretrained language model (PLM) without further fine-tuning.To this end, in this paper, we propose a simple yet effective unsupervised approach, PromptRank, based on the PLM with an encoder-decoder architecture.Specifically, PromptRank feeds the document into the encoder and calculates the probability of generating the candidate with a designed prompt by the decoder.We extensively evaluate the proposed PromptRank on six widely used benchmarks.PromptRank outperforms the SOTA approach MDERank, improving the F 1 score relatively by 34.18%, 24.87%, and 17.57% for 5, 10, and 15 returned results, respectively.This demonstrates the great potential of using prompt for unsupervised keyphrase extraction.We release our code at this url.

Developing countries are looking to satisfy ever-growing demand for education by leveraging the access and communication capabilities afforded by e-learning and the increasing range of open education resources made available through universities and development organisations globally. However a 'one size fits all', predominantly Western approach to developing and implementing educational initiatives has often failed in information and communication technology for development (ICT4D) projects. Over the past few years, we have been piloting and refining a learning design support strategy, entitled HEART: HEaring And Realizing Teaching-voice. HEART aims to enhance educators' learning design awareness and capability by eliciting and depicting the pedagogical beliefs underpinning a course or learning design. HEART has shown its potential to promote discussion and reflection of the beliefs and values that underpin course design. These beliefs can otherwise act as invisible but powerful obstacles to achieving the cross-cultural understandings necessary for effective e-learning design and implementation. This workshop will enable each participant to use the HEART visualization strategy to elicit and depict cultural-pedagogical beliefs relating to a teaching project or learning context of personal interest, demonstrating its ability to facilitate more effective cross-cultural learning design practice.