Table of Links Abstract and 1 Introduction Abstract and 1 Introduction 2 Survey with Industry Professionals 2 Survey with Industry Professionals 3 RQ1: Real-World use cases that necessitate output constraints 3 RQ1: Real-World use cases that necessitate output constraints 4 RQ2: Benefits of Applying Constraints to LLM Outputs and 4.1 Increasing Prompt-based development Efficiency 4 RQ2: Benefits of Applying Constraints to LLM Outputs and 4.1 Increasing Prompt-based development Efficiency 4.2 Integrating with Downstream Processes and Workflows 4.2 Integrating with Downstream Processes and Workflows 4.3 Satisfying UI and Product Requirements and 4.4 Improving User Experience, Trust, and Adoption 4.3 Satisfying UI and Product Requirements and 4.4 Improving User Experience, Trust, and Adoption 5 How to Articulate output constraints to LLMS and 5.1 The case for GUI: A Quick, Reliable, and Flexible Way of Prototyping Constraints 5 How to Articulate output constraints to LLMS and 5.1 The case for GUI: A Quick, Reliable, and Flexible Way of Prototyping Constraints 5.2 The Case for NL: More Intuitive and Expressive for Complex Constraints 5.2 The Case for NL: More Intuitive and Expressive for Complex Constraints 6 The Constraint maker Tool and 6.1 Iterative Design and User Feedback 6 The Constraint maker Tool and 6.1 Iterative Design and User Feedback 7 Conclusion and References 7 Conclusion and References A. The Survey Instrument A. The Survey Instrument 3 RQ1: REAL-WORLD USE CASES THAT NECESSITATE OUTPUT CONSTRAINTS Table 1 presents a taxonomy of six primary categories of use cases that require output constraints, each with representative real-world examples and quotes submitted by our respondents. These can be further divided into low-level and high-level constraints — low-level constraints ensure that model outputs adhere to a specific structure (e.g., JSON or markdown), instruct the model to perform pure multiple choices (e.g., sentiment classification), or dictate the length of the outputs; whereas high-level constraints enforce model outputs to respect semantic (e.g., must include or avoid specific terms or actions) or stylistic (e.g., follow certain style or tone) guidelines, while preventing hallucination. low-level high-level constraints structure multiple choices length semantic stylistic preventing hallucination. Below, we discuss a number of interesting insights that emerged from our analysis of the use cases: • Going beyond valid JSON. Note that recent advancements in instruction-tuning techniques have substantially improved the the chances of generating a valid JSON object upon user request [27, 29]. Nonetheless, our survey respondents believed that this was not enough and desired to have more precise control over the JSON schema (i.e., key/value pairs). One respondent stated their expectation as follows: “I expect the quiz [that the LLM makes given a few passages provided below] to have 1 correct answer and 3 incorrect ones. I want to have the output to be like a json with keys {"question": "...", "correct_answer": "...", "incorrect_answers": [...]}.” It is also worth mentioning that some respondents found that “few-shot prompts” — demonstrating the desired key/value pairs with several examples — tend to work “fairly well”. However, they concurred that having a formal guarantee of JSON schema would be greatly appreciated (see section 4.1 for their detailed rationales). • Going beyond valid JSON. desired to have more precise control over the JSON schema (i.e., key/value pairs). “I expect the quiz [that the LLM makes given a few passages provided below] to have 1 correct answer and 3 incorrect ones. I want to have the output to be like a json with keys {"question": "...", "correct_answer": "...", "incorrect_answers": [...]}.” “few-shot prompts” “fairly well” • Giving an answer without extra conversational prose. When asking an LLM to perform data classification or labeling, such as “[classifying sentiments as] Positive, Negative, Neutral, etc.,” respondents typically expect the model to only output the classification result (e.g. “Positive.”) without a trailing “explanation” (e.g., “Positive, since it referred to the movie as a ‘timeless masterpiece’...”), as the addition of explanation could potentially confuse the downstream parsing logic. This indicates a potential misalignment between a common training objective — where LLMs are often tailored to be conversational and provide rich details [2, 17, 33] — and certain specialized downstream use cases where software developers need LLMs to be succinct. Such use cases necessitate output constraints that are independent of the prompt that would help adapt a general-purpose model to meet specific user requirements. • Giving an answer without extra conversational prose. “[classifying sentiments as] Positive, Negative, Neutral, etc.,” only output the classification result without a trailing “explanation” • Conditioning the output on the input, but don’t “improvise!” One thread of high-level constraints places emphasis on directing the model to condition its output on specific content from the input. For example, the model’s response should semantically remain “in the same ballpark” as “the user’s original query” — “[the output of] a query about ‘fall jackets’ should be confined to clothing.” A particular instance of this is for LLMs to echo segments of the input in their output, occasionally with slight alterations. For example, “we want LLM to repeat input with some control tokens to indicate the mentions. e.g. input: ‘Obama was born in 1961.’,... , we want output to be ‘«Obama» was born in 1961.’” Nevertheless, respondents underscored the importance of the model not improvising beyond its input and instructions. For example, one respondent instructed an LLM to “annotate a method with debug statement,” anticipating the output would “ONLY include changes that add print statements to the method.” However, the LLM would frequently introduce additional “changes in syntax” that were unwarranted. One thread of high-level constraints places emphasis on directing the model condition its output on specific content from the input in the same ballpark” as “the user’s original query” — “[the output of] a query about ‘fall jackets’ should be confined to clothing.” “we want LLM to repeat input with some control tokens to indicate the mentions. e.g. input: ‘Obama was born in 1961.’,... , we want output to be ‘«Obama» was born in 1961.’” not improvising beyond its input and instructions. “annotate a method with debug statement,” “ONLY include changes that add print statements to the method.” This paper is available on arxiv under CC BY-NC-SA 4.0 DEED license. This paper is available on arxiv under CC BY-NC-SA 4.0 DEED license. available on arxiv Authors:
(1) Michael Xieyang Liu, Google Research, Pittsburgh, PA, USA (lxieyang@google.com);
(2) Frederick Liu, Google Research, Seattle, Washington, USA (frederickliu@google.com);
(3) Alexander J. Fiannaca, Google Research, Seattle, Washington, USA (afiannaca@google.com);
(4) Terry Koo, Google, Indiana, USA (terrykoo@google.com);
(5) Lucas Dixon, Google Research, Paris, France (ldixon@google.com);
(6) Michael Terry, Google Research, Cambridge, Massachusetts, USA (michaelterry@google.com);
(7) Carrie J. Cai, Google Research, Mountain View, California, USA (cjcai@google.com). Authors: Authors: (1) Michael Xieyang Liu, Google Research, Pittsburgh, PA, USA (lxieyang@google.com); (2) Frederick Liu, Google Research, Seattle, Washington, USA (frederickliu@google.com); (3) Alexander J. Fiannaca, Google Research, Seattle, Washington, USA (afiannaca@google.com); (4) Terry Koo, Google, Indiana, USA (terrykoo@google.com); (5) Lucas Dixon, Google Research, Paris, France (ldixon@google.com); (6) Michael Terry, Google Research, Cambridge, Massachusetts, USA (michaelterry@google.com); (7) Carrie J. Cai, Google Research, Mountain View, California, USA (cjcai@google.com).

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

Iterative

Google

Real-World Use Cases That Necessitate Output Constraints

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

How to Articulate Output Constraints to LLMS

"We Need Structured Output": Towards User-Centered Constraints on Large Language Model Output

How We Deployed an Online Survey to Users of an Internal Prompt-Based Prototyping Platform

The Benefits of Applying Constraints to LLM Outputs

How We Integrated Downstream Processes and Workflows

Satisfying UI and Product Requirements and Improving User Experience, Trust, and Adoption

How to Articulate Output Constraints to LLMS

"We Need Structured Output": Towards User-Centered Constraints on Large Language Model Output

How We Deployed an Online Survey to Users of an Internal Prompt-Based Prototyping Platform

The Benefits of Applying Constraints to LLM Outputs

How We Integrated Downstream Processes and Workflows

Satisfying UI and Product Requirements and Improving User Experience, Trust, and Adoption

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps