Create accountLogin

Recent searches

No recent searches

Search options

Not available on lingo.lol.
lingo.lol is one of the many independent Mastodon servers you can use to participate in the fediverse.
A place for linguists, philologists, and other lovers of languages.

Administered by:

Server stats:

70
active users

lingo.lol: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#z3

2 posts2 participants0 posts today
Public
José A. Alonso

Instantiation-based formalization of logical reasoning tasks using language models and logical solvers. ~ Mohammad Raza, Natasa Milic-Frayling. arxiv.org/abs/2501.16961 #LLMs #Reasoning #SMT #Z3

arXiv.orgInstantiation-based Formalization of Logical Reasoning Tasks using Language Models and Logical SolversRobustness of reasoning remains a significant challenge for large language models, and addressing it is essential for the practical applicability of AI-driven reasoning systems. We introduce Semantic Self-Verification (SSV), a novel approach that addresses the key challenge in combining language models with the rigor of logical solvers: to accurately formulate the reasoning problem from natural language to the formal language of the solver. SSV uses a consistency-based approach to produce strong abstract formalizations of problems using concrete instantiations that are generated by the model and verified by the solver. In addition to significantly advancing the overall reasoning accuracy over the state-of-the-art, a key novelty that this approach presents is a feature of verification that has near-perfect precision over a significant coverage of cases, as we demonstrate on open reasoning benchmarks. We propose such *near-certain reasoning* as a new approach to reduce the need for manual verification in many cases, taking us closer to more dependable and autonomous AI reasoning systems.
Public
Nadiah Kristensen

I recently read a paper by Kleshnina and others and used it to teach myself some evolutionary game theory techniques.

This is a little obscure, so I'll thread below about why this topic matters for humans and the environment 🧵

nadiah.org/2024/11/20/kleshnin

Nadiah Pardede Kristensen · Check if an iterated Prisoner’s Dilemma strategy is a subgame perfect Nash equilibriumI recently read a paper by Kleshnina et al. (2023), The effect of environmental information on evolution of cooperation in stochastic games, which provided an opportunity to teach myself about how to analyse iterated games. In particular, the problem they investigated admits 64 possible scenarios with 256 possible strategies each, and I was interested in writing code that could automate the analysis. The solution I eventually landed on (Github repo) used a combination of SymPy, NetworkX, SageMath, the Z3 Theorem Prover, and PyEDA for Boolean minimisation, but I think my approach could be improved.
#GameTheory#PrisonersDilemma#iteratedGame
Public
José A. Alonso

A closer look at logical reasoning with LLMs: The choice of tool matters. ~ Long Hei Matthew Lam, Ehsan Shareghi. arxiv.org/abs/2406.00284 #LLMs #ATP #Prover9 #SMT #Z3

arXiv.orgA Closer Look at Logical Reasoning with LLMs: The Choice of Tool MattersLogical reasoning serves as a cornerstone for human cognition. Recently, the emergence of Large Language Models (LLMs) has demonstrated promising progress in solving logical reasoning tasks effectively. To improve this capability, recent studies have delved into integrating LLMs with various symbolic solvers using diverse techniques and methodologies. While some combinations excel on specific datasets, others fall short. However, it remains unclear whether the variance in performance stems from the methodologies employed or the specific symbolic solvers utilized. Therefore, there is a lack of consistent comparison between symbolic solvers and how they influence LLM's logical reasoning ability. We perform experiments on LLMs integrated with 3 symbolic solvers: Z3, Pyke, and Prover9, and compare their performance on 3 logical reasoning datasets: ProofWriter, PrOntoQA, and FOLIO. Our findings indicate that when combined with LLMs Pyke's performance is significantly inferior to that of Prover9 and Z3. Z3's overall accuracy performance slightly surpasses Prover9, but Prover9 could execute more questions.
ExploreLive feeds
About