LLMs match or exceed state-of-the-art traditional methods for stabilizing numerical expressions in scientific software, succeeding on 97.9% of expressions where baselines fail to improve accuracy, but struggle with control flow and high-precision literals.
hub Canonical reference
In: Findings of the Association for Computational Linguistics: ACL 2023
Canonical reference. 83% of citing Pith papers cite this work as background.
12
Pith papers citing it
Background
83% of classified citations
hub tools
citation-role summary
background 5
other 1
citation-polarity summary
representative citing papers
Introduces TableGrid Navigation (TGN) and Progressive Inference Prompting (PIP) as training-free structured prompting frameworks that improve LLM performance on table question answering over baselines on TableBench and achieve SOTA on FeTaQa.
Anonymization placement in RAG—at the dataset or at the generated answer—creates observable differences in privacy protection versus response utility.
Persona induction in LLMs produces stable task-dependent cognitive performance shifts aligned with human patterns at 73.68%, and Dynamic Persona Routing outperforms static personas without retraining.
BLINK benchmark shows multimodal LLMs reach only 45-51 percent accuracy on core visual perception tasks where humans achieve 95 percent, indicating these abilities have not emerged.
Anthropogenic Regional Adaptation with GG-EZ improves cultural relevance in multimodal vision-language models for Southeast Asia by 5-15% while retaining over 98% of global performance.
LLMs can outperform DTA on index recommendations for some workloads but remain less reliable with practical adoption challenges.
PatMD improves harmful meme detection by retrieving misjudgment risk patterns to guide MLLMs, reporting 8.30% average F1 and 7.71% accuracy gains on 6,626 memes across 5 tasks.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
A survey reviewing benchmark data contamination in LLMs, its impact on evaluation, and alternative assessment approaches.
The book introduces the origins, mathematical setup, and optimization stages of RLHF including reward modeling, reinforcement learning, rejection sampling, and direct alignment algorithms.
This survey paper identifies opportunities for LLMs in low-resource language humanities research along with challenges in data accessibility, model adaptability, and cultural sensitivity.
citing papers explorer
-
Assessing Large Language Models for Stabilizing Numerical Expressions in Scientific Software
LLMs match or exceed state-of-the-art traditional methods for stabilizing numerical expressions in scientific software, succeeding on 97.9% of expressions where baselines fail to improve accuracy, but struggle with control flow and high-precision literals.
-
Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting
Introduces TableGrid Navigation (TGN) and Progressive Inference Prompting (PIP) as training-free structured prompting frameworks that improve LLM performance on table question answering over baselines on TableBench and achieve SOTA on FeTaQa.
-
A Case Study on the Impact of Anonymization Along the RAG Pipeline
Anonymization placement in RAG—at the dataset or at the generated answer—creates observable differences in privacy protection versus response utility.
-
A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities
Persona induction in LLMs produces stable task-dependent cognitive performance shifts aligned with human patterns at 73.68%, and Dynamic Persona Routing outperforms static personas without retraining.
-
BLINK: Multimodal Large Language Models Can See but Not Perceive
BLINK benchmark shows multimodal LLMs reach only 45-51 percent accuracy on core visual perception tasks where humans achieve 95 percent, indicating these abilities have not emerged.
-
Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
Anthropogenic Regional Adaptation with GG-EZ improves cultural relevance in multimodal vision-language models for Southeast Asia by 5-15% while retaining over 98% of global performance.
-
Evaluating the Practical Effectiveness of LLM-Driven Index Tuning with Microsoft Database Tuning Advisor
LLMs can outperform DTA on index recommendations for some workloads but remain less reliable with practical adoption challenges.
-
Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval
PatMD improves harmful meme detection by retrieving misjudgment risk patterns to guide MLLMs, reporting 8.30% average F1 and 7.71% accuracy gains on 6,626 memes across 5 tasks.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
Benchmark Data Contamination of Large Language Models: A Survey
A survey reviewing benchmark data contamination in LLMs, its impact on evaluation, and alternative assessment approaches.
-
Reinforcement Learning from Human Feedback
The book introduces the origins, mathematical setup, and optimization stages of RLHF including reward modeling, reinforcement learning, rejection sampling, and direct alignment algorithms.
-
Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research
This survey paper identifies opportunities for LLMs in low-resource language humanities research along with challenges in data accessibility, model adaptability, and cultural sensitivity.