REVIEW 22 cited by
A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
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
read the original abstract
GPT series models, such as GPT-3, CodeX, InstructGPT, ChatGPT, and so on, have gained considerable attention due to their exceptional natural language processing capabilities. However, despite the abundance of research on the difference in capabilities between GPT series models and fine-tuned models, there has been limited attention given to the evolution of GPT series models' capabilities over time. To conduct a comprehensive analysis of the capabilities of GPT series models, we select six representative models, comprising two GPT-3 series models (i.e., davinci and text-davinci-001) and four GPT-3.5 series models (i.e., code-davinci-002, text-davinci-002, text-davinci-003, and gpt-3.5-turbo). We evaluate their performance on nine natural language understanding (NLU) tasks using 21 datasets. In particular, we compare the performance and robustness of different models for each task under zero-shot and few-shot scenarios. Our extensive experiments reveal that the overall ability of GPT series models on NLU tasks does not increase gradually as the models evolve, especially with the introduction of the RLHF training strategy. While this strategy enhances the models' ability to generate human-like responses, it also compromises their ability to solve some tasks. Furthermore, our findings indicate that there is still room for improvement in areas such as model robustness.
Forward citations
Cited by 22 Pith papers
-
TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla
TigerCoder is a fine-tuned Bangla code-generation LLM family that posts 0.82 Pass@1 on the new MBPP-Bangla benchmark, but its gains partly come from model selection on the test set.
-
Another Turn, Better Output? A Turn-Wise Analysis of Iterative LLM Prompting
Iterative LLM refinement helps early in ideation and code, but in math only late under elaboration prompting; vague feedback tends to plateau or degrade quality.
-
Understood: Real-Time Communication Support for Adults with ADHD Using Mixed Reality
A HoloLens-based mixed reality assistant for adults with ADHD reduced conversation pause and off-topic recovery times in a within-subjects lab study of 10 participants.
-
RecRankerEval: A Flexible and Extensible Framework for Top-k LLM-based Recommendation
A reimplementation of RecRanker shows its pointwise variant's high top-k scores come from ground-truth data leakage in the prompts, and the new RecRankerEval framework finds listwise tuning, DBSCAN sampling, XSimGCL, ...
-
Un-considering Contextual Information: Assessing LLMs' Understanding of Indexical Elements
A 1,600-question English benchmark shows LLMs interpret 'I' almost perfectly while struggling with 'you', 'here', and 'tomorrow', with quotation affecting each indexical differently.
-
CODEMENV: Benchmarking Large Language Models on Code Migration
CODEMENV provides 922 examples and three tasks for evaluating LLMs on cross-version code migration, finding models are much better at migrating old code to new versions (up to 43.84% pass@1) than the reverse.
-
Large Language Models in the Task of Automatic Validation of Text Classifier Predictions
LLM-based annotators using token-probability thresholds, RAG, and reasoning fine-tuning matched or exceeded human annotator quality on a proprietary 250-class intent-validation task.
-
Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel Planning
Multi-agent LLM travel planners are frequently deceived by injected fake listings, coordinated fake reviews, and multi-round scam conversations, and a simple anti-fraud reviewer helps only some models.
-
Efficient Code Analysis via Graph Representation Learning-Guided Large Language Models
A GNN selects suspicious subgraphs of a Python project and an LLM judges only those subgraphs, beating direct whole-project LLM analysis on PyPI malware benchmarks.
-
LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging
RecovSlicing recovers dynamic data dependencies from partially recorded execution traces by using a language model to reconstruct missed variable values and aliases.
-
SAGE: A Context-Aware Approach for Mining Privacy Requirements Relevant Reviews from Mental Health Apps
SAGE combines domain-specific NLI hypotheses with a zero-shot GPT classifier to identify privacy-related app reviews, reporting F1 0.85 on 1,376 labels and extracting 748 new privacy reviews.
-
A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs
STReason uses in-context learning to convert spatio-temporal queries into executable programs with specialized modules, outperforming plain LLMs on a new 150-query benchmark.
-
MATE: LLM-Powered Multi-Agent Translation Environment for Accessibility Applications
MATE is an open-source multi-agent system for accessibility that uses a fine-tuned BERT model, trained on a new AI-generated dataset, to recognize and execute modality conversion tasks.
-
StepProof: Step-by-step verification of natural language mathematical proofs
Decomposing natural-language proofs into sentence-level formal subproofs improves autoformalization success rates and efficiency compared with whole-proof formalization.
-
Towards medical AI misalignment: a preliminary study
A custom role-playing prompt called the Goofy Game made four major LLMs produce plausible but incorrect medical recommendations.
-
Evaluating Large Language Models for Diacritic Restoration in Romanian Texts: A Comparative Study
GPT-4o with a three-shot prompt is the best tested LLM for Romanian diacritic restoration (TAS 0.9639), beating an echo baseline by about 19%.
-
Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models
A dual-retrieval, threshold-gated, full-parameter fine-tuned code LLM (SelRepair) reports state-of-the-art exact-match patch generation on Tufano and VulRepair benchmarks.
-
CMER: A Context-Aware Approach for Mining Ethical Concern-related App Reviews
A hybrid NLI-plus-LLM pipeline with finance-specific hypotheses extracted 2,178 manually validated privacy/security reviews from mobile investment app reviews.
-
Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production Challenges
A proof-of-concept multi-agent GPT system for microbial protein literature extraction shows both fine-tuning and prompt engineering improve cosine-similarity scores, with fine-tuning slightly ahead but more variable.
-
A Practical Guide for Supporting Formative Assessment and Feedback Using Generative AI
A narrative review that aligns generative AI tools with formative assessment principles, provides classroom prompt examples, and identifies missing evaluation metrics for AI feedback.
-
Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking
A benchmark and two low-cost tricks (weight refactorization and momentum reset) that make low-rank LLM pre-training competitive with GaLore and Fira at about 25% lower memory.
-
ICH-Qwen: A Large Language Model Towards Chinese Intangible Cultural Heritage
They fine-tuned Qwen2.5-7B on Chinese intangible cultural heritage texts to build ICH-Qwen, and report n-gram metric wins over general LLMs on 100-sample ICH QA tasks.
Discussion (0). Sign in to comment.