Effective Messages of Support and Encouragement

Share This Post

From time to time, we all experience situations that leave us feeling down or doubting our abilities. In such times, we need the support of others to pick us up. Whether such scenarios occur in our personal lives or at work, they can negatively impact our productivity.

For this reason, businesses need to become adept at sharing meaningful and effective messages of support and encouragement. Let’s dive right into scenarios that would warrant a message of support and what one can say in that message.

Messages of support and encouragement during personal moments

In times of sickness

Sickness and extended sickness in particular is stressful to deal with. It gets even harder when an employee feels anxious about letting teammates down. Show a sick employee that the company cares by sharing messages of support and encouragement.

Some companies opt to buy a card and have each team mate write a personal message. As each has a different relationship, the messages will be more meaningful than a generic ‘Get well soon’.

When employees suffer the loss of a loved one

Losing a loved one is never easy. While on compassionate leave, managers should organise an official message of support and encouragement from the company. Craft something heartfelt to convey concern.

“Thinking of you and wishing you moments of peace and comfort as you remember a friend who was so close to you.”

It is also okay to include a sympathy basket with the message. It may contain items like comfort foods, poems of comfort or bible verses of comfort and a paid subscription to a grief counsellor.

When an employee graduates

A simple but heartfelt message of support when an employee graduates or acquires a new level of education is a sure way to increase morale.

Messages of support and encouragement for workplace scenarios

When employees are trying to acquire a client

When employees have a client pitch or presentation, show you believe in them with a message of support and encouragement. Write a message that reminds them of their abilities and the preparations they have made to be able to take on the task.

Such a message will boost confidence and reiterate the trust a manager has in their employees.

When employees lose a client

What happens when employees fail to acquire that client or even lose one? Depending on your management style, you might react in one of 2 ways, blame or encouragement. Some managers believe in learning from mistakes, showing support and encouragement and moving on to the next challenge.

A message to say, ‘We did our best, we shall win them next time.’ Or one to say ‘Great effort team. We’ll get them next time’ can show support and encouragement.

When a manager leaves

From time to time, managers may leave the job for a new opportunity. If they have been a good manager, their absence will be felt on the management level and with their team.

The messages of support and encouragement in this instance will come from several sections of employees.

From management:

Management should send a message of gratitude and farewell to a colleague they have served with. Traditionally gifts are also given.

From employees:

The relationship that direct reports have with their manager is different from one the manager will have with fellow managers. If the manager has been a good one, he or she will have been a source of encouragement, a mentor, a champion and an advocate for their team. The team may also want to share their own messages of support and encouragement to their manager.

From the manager:

Messages of support and encouragement may also come from the manager. Someone leaving a company can be destabilising to other employees, particularly if this person has been a pillar. A cold exit will have a negative effect on continuing employees. You may even see a decline in job satisfaction and productivity in the wake of a manager’s exit.

To mitigate this, a message of support and encouragement from the exiting employee to their team is a good idea. This message may summarise their experience leading that team and reiterate the confidence the leader has in their abilities. If a successor has already been named, an endorsement of this person can go a long way in ensuring a smooth transition.

When someone gets a promotion

Messages of support and encouragement are also welcome in times of celebration. Show teammates and employees you wish them well when they rise through the ranks by sending a congratulatory message.

In this type of message, tell them you are proud of them, that they deserve the new position and that you have faith they will excel.

When someone is let go

People may be let go for a range of reasons. In some cases, it has nothing to do with their behaviour or performance. The COVID pandemic for instance saw many workers laid off so that businesses could survive.

Despite knowing this, it is still natural for employees to think they were let go due to a failing on their part. In this scenario it is a good idea to let employees know why they are being let go.

A message of support and encouragement may include a mention of the achievements of said employee, an offer to write them a recommendation and an endorsement of their abilities. For instance:

“We have had the pleasure of witnessing your commitment and hard work for the years you have been with us. Thank you for all your hard work. We know that your excellent people skills, leadership capabilities and team work will serve you no matter where you land. Please let us know if you need a recommendation from us. We are confident that you will do great things on your next venture.”

In Summary

One thing to keep top of mind when sending messages of support and encouragement is to make them personal. Tailor them to the specific employee and the specific situation, otherwise they will ring hollow.

Messages of encouragement show employees that you are truly concerned about their wellbeing. Aside from that, they can increase employee trust, loyalty and motivation.

Remember, messages of support and encouragement aren’t only valid for negative situations. Send one to help a colleague or employee celebrate.

The post Effective Messages of Support and Encouragement appeared first on The 6Q Blog.

Subscribe To Our Newsletter

Get updates and learn from the best

More To Explore

Uncategorized

How HR Can Help Build a Safe and Healthy Workplace Culture

Establishing a safe and healthy workplace is crucial for any organisation. As a human resources (HR) manager, you play a vital role in fostering a

douglas.campbell@wellstar360.com September 21, 2023

Uncategorized

Distilling step-by-step: Outperforming larger language models with less training data and smaller model sizes

Posted by Cheng-Yu Hsieh, Student Researcher, and Chen-Yu Lee, Research Scientist, Cloud AI Team

Large language models (LLMs) have enabled a new data-efficient learning paradigm wherein they can be used to solve unseen new tasks via zero-shot or few-shot prompting. However, LLMs are challenging to deploy for real-world applications due to their sheer size. For instance, serving a single 175 billion LLM requires at least 350GB of GPU memory using specialized infrastructure, not to mention that today’s state-of-the-art LLMs are composed of over 500 billion parameters. Such computational requirements are inaccessible for many research teams, especially for applications that require low latency performance.

To circumvent these deployment challenges, practitioners often choose to deploy smaller specialized models instead. These smaller models are trained using one of two common paradigms: fine-tuning or distillation. Fine-tuning updates a pre-trained smaller model (e.g., BERT or T5) using downstream manually-annotated data. Distillation trains the same smaller models with labels generated by a larger LLM. Unfortunately, to achieve comparable performance to LLMs, fine-tuning methods require human-generated labels, which are expensive and tedious to obtain, while distillation requires large amounts of unlabeled data, which can also be hard to collect.

In “Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes”, presented at ACL2023, we set out to tackle this trade-off between model size and training data collection cost. We introduce distilling step-by-step, a new simple mechanism that allows us to train smaller task-specific models with much less training data than required by standard fine-tuning or distillation approaches that outperform few-shot prompted LLMs’ performance. We demonstrate that the distilling step-by-step mechanism enables a 770M parameter T5 model to outperform the few-shot prompted 540B PaLM model using only 80% of examples in a benchmark dataset, which demonstrates a more than 700x model size reduction with much less training data required by standard approaches.

While LLMs offer strong zero and few-shot performance, they are challenging to serve in practice. On the other hand, traditional ways of training small task-specific models require a large amount of training data. Distilling step-by-step provides a new paradigm that reduces both the deployed model size as well as the number of data required for training.

Distilling step-by-step

The key idea of distilling step-by-step is to extract informative natural language rationales (i.e., intermediate reasoning steps) from LLMs, which can in turn be used to train small models in a more data-efficient way. Specifically, natural language rationales explain the connections between the input questions and their corresponding outputs. For example, when asked, “Jesse’s room is 11 feet long and 15 feet wide. If she already has 16 square feet of carpet, how much more carpet does she need to cover the whole floor?”, an LLM can be prompted by the few-shot chain-of-thought (CoT) prompting technique to provide intermediate rationales, such as, “Area = length * width. Jesse’s room has 11 * 15 square feet.” That better explains the connection from the input to the final answer, “(11 * 15 ) – 16”. These rationales can contain relevant task knowledge, such as “Area = length * width”, that may originally require many data for small models to learn. We utilize these extracted rationales as additional, richer supervision to train small models, in addition to the standard task labels.

Overview on distilling step-by-step: First, we utilize CoT prompting to extract rationales from an LLM. We then use the generated rationales to train small task-specific models within a multi-task learning framework, where we prepend task prefixes to the input examples and train the model to output differently based on the given task prefix.

Distilling step-by-step consists of two main stages. In the first stage, we leverage few-shot CoT prompting to extract rationales from LLMs. Specifically, given a task, we prepare few-shot exemplars in the LLM input prompt where each example is composed of a triplet containing: (1) input, (2) rationale, and (3) output. Given the prompt, an LLM is able to mimic the triplet demonstration to generate the rationale for any new input. For instance, in a commonsense question answering task, given the input question “Sammy wanted to go to where the people are. Where might he go? Answer Choices: (a) populated areas, (b) race track, (c) desert, (d) apartment, (e) roadblock”, distilling step-by-step provides the correct answer to the question, “(a) populated areas”, paired with the rationale that provides better connection from the question to the answer, “The answer must be a place with a lot of people. Of the above choices, only populated areas have a lot of people.” By providing CoT examples paired with rationales in the prompt, the in-context learning ability allows LLMs to output corresponding rationales for future unseen inputs.

We use the few-shot CoT prompting, which contains both an example rationale (highlighted in green) and a label (highlighted in blue), to elicit rationales from an LLM on new input examples. The example is from a commonsense question answering task.

After the rationales are extracted, in the second stage, we incorporate the rationales in training small models by framing the training process as a multi-task problem. Specifically, we train the small model with a novel rationale generation task in addition to the standard label prediction task. The rationale generation task enables the model to learn to generate the intermediate reasoning steps for the prediction, and guides the model to better predict the resultant label. We prepend task prefixes (i.e., [label] and [rationale] for label prediction and rationale generation, respectively) to the input examples for the model to differentiate the two tasks.

Experimental setup

In the experiments, we consider a 540B PaLM model as the LLM. For task-specific downstream models, we use T5 models. For CoT prompting, we use the original CoT prompts when available and curate our own examples for new datasets. We conduct the experiments on four benchmark datasets across three different NLP tasks: e-SNLI and ANLI for natural language inference; CQA for commonsense question answering; and SVAMP for arithmetic math word problems. We include two sets of baseline methods. For comparison to few-shot prompted LLMs, we compare to few-shot CoT prompting with a 540B PaLM model. In the paper, we also compare standard task-specific model training to both standard fine-tuning and standard distillation. In this blogpost, we will focus on the comparisons to standard fine-tuning for illustration purposes.

Less training data

Compared to standard fine-tuning, the distilling step-by-step method achieves better performance using much less training data. For instance, on the e-SNLI dataset, we achieve better performance than standard fine-tuning when using only 12.5% of the full dataset (shown in the upper left quadrant below). Similarly, we achieve a dataset size reduction of 75%, 25% and 20% on ANLI, CQA, and SVAMP.

Distilling step-by-step compared to standard fine-tuning using 220M T5 models on varying sizes of human-labeled datasets. On all datasets, distilling step-by-step is able to outperform standard fine-tuning, trained on the full dataset, by using much less training examples.

Smaller deployed model size

Compared to few-shot CoT prompted LLMs, distilling step-by-step achieves better performance using much smaller model sizes. For instance, on the e-SNLI dataset, we achieve better performance than 540B PaLM by using a 220M T5 model. On ANLI, we achieve better performance than 540B PaLM by using a 770M T5 model, which is over 700X smaller. Note that on ANLI, the same 770M T5 model struggles to match PaLM’s performance using standard fine-tuning.

We perform distilling step-by-step and standard fine-tuning on varying sizes of T5 models and compare their performance to LLM baselines, i.e., Few-shot CoT and PINTO Tuning. Distilling step-by-step is able to outperform LLM baselines by using much smaller models, e.g., over 700× smaller models on ANLI. Standard fine-tuning fails to match LLM’s performance using the same model size.

Distilling step-by-step outperforms few-shot LLMs with smaller models using less data

Finally, we explore the smallest model sizes and the least amount of data for distilling step-by-step to outperform PaLM’s few-shot performance. For instance, on ANLI, we surpass the performance of the 540B PaLM using a 770M T5 model. This smaller model only uses 80% of the full dataset. Meanwhile, we observe that standard fine-tuning cannot catch up with PaLM’s performance even using 100% of the full dataset. This suggests that distilling step-by-step simultaneously reduces the model size as well as the amount of data required to outperform LLMs.

We show the minimum size of T5 models and the least amount of human-labeled examples required for distilling step-by-step to outperform LLM’s few-shot CoT by a coarse-grained search. Distilling step-by-step is able to outperform few-shot CoT using not only much smaller models, but it also achieves so with much less training examples compared to standard fine-tuning.

Conclusion

We propose distilling step-by-step, a novel mechanism that extracts rationales from LLMs as informative supervision in training small, task-specific models. We show that distilling step-by-step reduces both the training dataset required to curate task-specific smaller models and the model size required to achieve, and even surpass, a few-shot prompted LLM’s performance. Overall, distilling step-by-step presents a resource-efficient paradigm that tackles the trade-off between model size and training data required.

Availability on Google Cloud Platform

Distilling step-by-step is available for private preview on Vertex AI. If you are interested in trying it out, please contact vertex-llm-tuning-preview@google.com with your Google Cloud Project number and a summary of your use case.

Acknowledgements

This research was conducted by Cheng-Yu Hsieh, Chun-Liang Li, Chih-Kuan Yeh, Hootan Nakhost, Yasuhisa Fujii, Alexander Ratner, Ranjay Krishna, Chen-Yu Lee, and Tomas Pfister. Thanks to Xiang Zhang and Sergey Ioffe for their valuable feedback.