Pith. sign in

REVIEW 3 cited by

Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.09185 v1 pith:SPH564SW submitted 2023-02-17 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords modelsconstraintgenerativepromptanalyzeboundingcausesconstraints
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The limits of open-ended generative models are unclear, yet increasingly important. What causes them to succeed and what causes them to fail? In this paper, we take a prompt-centric approach to analyzing and bounding the abilities of open-ended generative models. We present a generic methodology of analysis with two challenging prompt constraint types: structural and stylistic. These constraint types are categorized into a set of well-defined constraints that are analyzable by a single prompt. We then systematically create a diverse set of simple, natural, and useful prompts to robustly analyze each individual constraint. Using the GPT-3 text-davinci-002 model as a case study, we generate outputs from our collection of prompts and analyze the model's generative failures. We also show the generalizability of our proposed method on other large models like BLOOM and OPT. Our results and our in-context mitigation strategies reveal open challenges for future research. We have publicly released our code at https://github.com/SALT-NLP/Bound-Cap-LLM.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Knowledge Conceptualization Impacts RAG Efficacy

    cs.AI 2025-07 conditional novelty 6.0 of 10

    An empirical study showing that both schema complexity and representation format affect how well GPT-4o generates SPARQL queries from competency questions, with mixed results across two knowledge graph families.

  2. Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks

    cs.SE 2025-06 conditional novelty 6.0 of 10

    Across ten software engineering tasks and four LLMs, no prompting technique wins consistently; ES-KNN is best on many tasks, some techniques underperform the baseline, and USC is best for code QA and code generation.

  3. A Large Language Model-Enabled Control Architecture for Dynamic Resource Capability Exploration in Multi-Agent Manufacturing Systems

    cs.MA 2025-05 conditional novelty 4.0 of 10

    An LLM-based central controller in a simulated manufacturing system dynamically reassigns robot capabilities during breakdowns and completes more parts than the baseline control framework.

Pith tools