Foundational challenges in assuring alignment and safety of large language models

U Anwar, A Saparov, J Rando, D Paleka… - arxiv preprint arxiv …, 2024 - arxiv.org
This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

LLM4SR: A Survey on Large Language Models for Scientific Research

Z Luo, Z Yang, Z Xu, W Yang, X Du - arxiv preprint arxiv:2501.04306, 2025 - arxiv.org
In recent years, the rapid advancement of Large Language Models (LLMs) has transformed
the landscape of scientific research, offering unprecedented support across various stages …

Code repair with llms gives an exploration-exploitation tradeoff

H Tang, K Hu, J Zhou, SC Zhong… - Advances in …, 2025 - proceedings.neurips.cc
Iteratively improving and repairing source code with large language models (LLMs), known
as refinement, has emerged as a popular way of generating programs that would be too …

Reasoning abilities of large language models: In-depth analysis on the abstraction and reasoning corpus

S Lee, W Sim, D Shin, W Seo, J Park, S Lee… - ACM Transactions on …, 2024 - dl.acm.org
The existing methods for evaluating the inference abilities of Large Language Models
(LLMs) have been predominantly results-centric, making it challenging to assess the …

Explaining Datasets in Words: Statistical Models with Natural Language Parameters

R Zhong, H Wang, D Klein… - Advances in Neural …, 2025 - proceedings.neurips.cc
To make sense of massive data, we often first fit simplified models and then interpret the
parameters; for example, we cluster the text embeddings and then interpret the mean …

Automated statistical model discovery with language models

MY Li, EB Fox, ND Goodman - arxiv preprint arxiv:2402.17879, 2024 - arxiv.org
Statistical model discovery involves a challenging search over a vast space of models
subject to domain-specific modeling constraints. Efficiently searching over this space …

DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines

A Singhvi, M Shetty, S Tan, C Potts, K Sen… - arxiv preprint arxiv …, 2023 - arxiv.org
Chaining language model (LM) calls as composable modules is fueling a new powerful way
of programming. However, ensuring that LMs adhere to important constraints remains a key …

Literature meets data: A synergistic approach to hypothesis generation

H Liu, Y Zhou, M Li, C Yuan, C Tan - arxiv preprint arxiv:2410.17309, 2024 - arxiv.org
AI holds promise for transforming scientific processes, including hypothesis generation. Prior
work on hypothesis generation can be broadly categorized into theory-driven and data …

Neural networks for abstraction and reasoning

M Bober-Irizar, S Banerjee - Scientific Reports, 2024 - nature.com
For half a century, artificial intelligence research has attempted to reproduce the human
qualities of abstraction and reasoning-creating computer systems that can learn new …

Doing experiments and revising rules with natural language and probabilistic reasoning

WT Piriyakulkij, C Langenfeld, TA Le, K Ellis - arxiv preprint arxiv …, 2024 - arxiv.org
We give a model of how to infer natural language rules by doing experiments. The model
integrates Large Language Models (LLMs) with Monte Carlo algorithms for probabilistic …