Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.
Calibrate before use: Improving few- shot performance of language models
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
An unsupervised technique extracts latent yes-no knowledge from language model activations by locating a direction that satisfies logical consistency properties, outperforming zero-shot accuracy by 4% on average across models and datasets.
UA-Legal-Bench is a new five-task benchmark for Ukrainian legal reasoning that demonstrates task-dependent few-shot prompting effects and the need for macro-F1 over accuracy on imbalanced classes.
PRIME is a new evaluation framework that creates calibrated conflicts in LLM prompts and finds conflict type affects model behavior more than scale.
Tokenizer fertility varies 2.5x across 25 European languages with domain-invariant rankings, morphological fragmentation in high-fertility cases, and a Ukrainian penalty from pre-training underrepresentation.
LLMs exhibit an accumulated message effect where conversation history polarity biases subsequent judgments, stronger for high-entropy items, independent of context length, and with a negativity bias.
Fine-tuning 7B code LLMs on a custom multi-file DSL dataset achieves structural fidelity of 1.00, high exact-match accuracy, and practical utility validated by expert survey and execution checks.
An Explicit Logic Channel of LLM, VFM and probabilistic inference validates and improves zero-shot MLLMs via Consistency Rate without ground-truth labels.
Scaling and instruction tuning increase sycophancy in LLMs on opinion and fact tasks, but a synthetic data fine-tuning intervention reduces it on held-out prompts.
Emergent abilities are capabilities present in large language models but absent in smaller ones and cannot be predicted by extrapolating smaller model performance.
In-context learning shows persistent interference from prior examples, with more misleading linear examples degrading quadratic predictions and training curricula modulating recovery speed.
SSAS improves LLM sentiment prediction consistency and data quality by up to 30% on three review datasets via syntactic and semantic context assessment summarization.
On a controlled Turkish dataset of 147 examples, few-shot prompting lets some LLMs match or beat a supervised BERT baseline for LVC detection, though results are highly sensitive to prompt design.
citing papers explorer
-
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.
-
Discovering Latent Knowledge in Language Models Without Supervision
An unsupervised technique extracts latent yes-no knowledge from language model activations by locating a direction that satisfies logical consistency properties, outperforming zero-shot accuracy by 4% on average across models and datasets.
-
UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning
UA-Legal-Bench is a new five-task benchmark for Ukrainian legal reasoning that demonstrates task-dependent few-shot prompting effects and the need for macro-F1 over accuracy on imbalanced classes.
-
PRIME: Evaluating Prompt Resolution Under Incompatible Instructions in LLMs
PRIME is a new evaluation framework that creates calibrated conflicts in LLM prompts and finds conflict type affects model behavior more than scale.
-
The Tokenizer Tax Across 25 European Languages: Domain Invariance, Cross-Lingual Few-Shot Effects, and the Ukrainian Penalty
Tokenizer fertility varies 2.5x across 25 European languages with domain-invariant rankings, morphological fragmentation in high-fertility cases, and a Ukrainian penalty from pre-training underrepresentation.
-
AMEL: Accumulated Message Effects on LLM Judgments
LLMs exhibit an accumulated message effect where conversation history polarity biases subsequent judgments, stronger for high-entropy items, independent of context length, and with a negativity bias.
-
Leveraging LLMs for Multi-File DSL Code Generation: An Industrial Case Study
Fine-tuning 7B code LLMs on a custom multi-file DSL dataset achieves structural fidelity of 1.00, high exact-match accuracy, and practical utility validated by expert survey and execution checks.
-
Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks
An Explicit Logic Channel of LLM, VFM and probabilistic inference validates and improves zero-shot MLLMs via Consistency Rate without ground-truth labels.
-
Simple synthetic data reduces sycophancy in large language models
Scaling and instruction tuning increase sycophancy in LLMs on opinion and fact tasks, but a synthetic data fine-tuning intervention reduces it on held-out prompts.
-
Emergent Abilities of Large Language Models
Emergent abilities are capabilities present in large language models but absent in smaller ones and cannot be predicted by extrapolating smaller model performance.
-
When Context Sticks: Studying Interference in In-Context Learning
In-context learning shows persistent interference from prior examples, with more misleading linear examples degrading quadratic predictions and training curricula modulating recovery speed.
-
Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)
SSAS improves LLM sentiment prediction consistency and data quality by up to 30% on three review datasets via syntactic and semantic context assessment summarization.
-
Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification
On a controlled Turkish dataset of 147 examples, few-shot prompting lets some LLMs match or beat a supervised BERT baseline for LVC detection, though results are highly sensitive to prompt design.