Fork-think with confidence identifies forking points via model confidence in a single path before sampling continuations, cutting tokens up to 30% and runtime up to 57% on reasoning benchmarks while matching or exceeding parallel thinking performance.
The effect of sampling temperature on problem solving in large language models
10 Pith papers cite this work, alongside 138 external citations. Polarity classification is still indexing.
10
Pith papers citing it
138
external citations · OpenAlex
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
SPAGBias reveals that LLMs form nuanced gender associations with specific urban micro-spaces that exceed real-world distributions and produce failures in planning and descriptive tasks.
A framework learns context-sensitive constraints automatically from LLM outputs to enforce perfect adherence during generation without manual specification.
RADAGAS-GPT4o achieves a 22.73% bypass rate against 10 WAFs, succeeding more against AI/ML-based firewalls than rule-based ones.
Maistros 8B is a new state-of-the-art open-weights Greek LLM built via knowledge distillation from large reasoning models on the CulturaQA dataset.
ContentFuzz rewrites posts with LLM guidance from stance model confidence to flip machine labels without altering human intent, tested across four models and three datasets in two languages.
LLMs achieve higher accuracy than humans on compositional imagery tasks previously argued to require pictorial representations, supporting emergent propositional mental imagery in AI.
Kernel ridge regression combined with mRMR feature selection improves prediction of full benchmark scores from question subsets over existing efficient benchmarking techniques.
The paper outlines opportunities, limitations, and practical parameters for integrating LLMs into qualitative research while aligning with epistemological commitments like reflexivity and interpretive judgment.
citing papers explorer
-
Fork-Think with Confidence
Fork-think with confidence identifies forking points via model confidence in a single path before sampling continuations, cutting tokens up to 30% and runtime up to 57% on reasoning benchmarks while matching or exceeding parallel thinking performance.
-
SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models
SPAGBias reveals that LLMs form nuanced gender associations with specific urban micro-spaces that exceed real-world distributions and produce failures in planning and descriptive tasks.
-
Learning and Enforcing Context-Sensitive Control for LLMs
A framework learns context-sensitive constraints automatically from LLM outputs to enforce perfect adherence during generation without manual specification.
-
Adversarial SQL Injection Generation with LLM-Based Architectures
RADAGAS-GPT4o achieves a 22.73% bypass rate against 10 WAFs, succeeding more against AI/ML-based firewalls than rule-based ones.
-
Maistros: A Greek Large Language Model Adapted Through Knowledge Distillation From Large Reasoning Models
Maistros 8B is a new state-of-the-art open-weights Greek LLM built via knowledge distillation from large reasoning models on the CulturaQA dataset.
-
Content Fuzzing for Escaping Information Cocoons on Digital Social Media
ContentFuzz rewrites posts with LLM guidance from stance model confidence to flip machine labels without altering human intent, tested across four models and three datasets in two languages.
-
Artificial Phantasia: Emergent Mental Imagery in Large Language Models
LLMs achieve higher accuracy than humans on compositional imagery tasks previously argued to require pictorial representations, supporting emergent propositional mental imagery in AI.
-
Efficient Benchmarking Is Just Feature Selection and Multiple Regression
Kernel ridge regression combined with mRMR feature selection improves prediction of full benchmark scores from question subsets over existing efficient benchmarking techniques.
-
LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations
The paper outlines opportunities, limitations, and practical parameters for integrating LLMs into qualitative research while aligning with epistemological commitments like reflexivity and interpretive judgment.
- Fine-grained Claim-level RAG Benchmark for Law