arxiv: 2605.09519 · v1 · submitted 2026-05-10 · 💻 cs.AI · cs.LO

Recognition: 2 theorem links

· Lean Theorem

Weighted Rules under the Stable Model Semantics

Joohyung Lee , Yi Wang

Authors on Pith no claims yet

Pith reviewed 2026-05-12 03:31 UTC · model grok-4.3

classification 💻 cs.AI cs.LO

keywords weighted rulesstable model semanticsanswer set programmingMarkov logicprobabilistic inferenceinconsistency resolutionmodel ranking

0 comments

The pith

Weighted rules extend stable model semantics to support probabilities, ranking, and inconsistency resolution.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper defines weighted rules inside stable model semantics by adapting log-linear models. This change targets the strict determinism of answer set programs so that conflicting rules can coexist and models can be ranked or assigned probabilities. A reader would care because the extension adds statistical inference tools directly to logical reasoning without leaving the stable model framework. The work also supplies formal comparisons to related languages. If the construction holds, it turns deterministic programs into objects that can be analyzed with probabilistic methods.

Core claim

We introduce the concept of weighted rules under the stable model semantics following the log-linear models of Markov Logic. This provides versatile methods to overcome the deterministic nature of the stable model semantics, such as resolving inconsistencies in answer set programs, ranking stable models, associating probability to stable models, and applying statistical inference to computing weighted stable models. We also present formal comparisons with related formalisms, such as answer set programs, Markov Logic, ProbLog, and P-log.

What carries the argument

Weighted rules: ordinary rules of an answer set program each carrying a numeric weight that contributes to the total score or probability of the stable models that satisfy them.

If this is right

Inconsistencies in answer set programs can be resolved by assigning lower weights to conflicting rules.
Stable models can be ranked by the sum of weights of the rules they satisfy.
Each stable model receives a probability proportional to the exponential of its total weight.
Statistical inference methods can be applied to compute or approximate weighted stable models.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The weighted semantics could support parameter learning from data by maximizing the likelihood of observed models.
Hybrid systems might combine the formalism with neural networks to learn weights for symbolic rules.
Approximate inference algorithms developed for Markov Logic could be adapted to run directly on weighted answer set programs.

Load-bearing premise

The weighting mechanism can be integrated into stable model semantics while preserving key properties and delivering the claimed probabilistic and inference capabilities without introducing inconsistencies or losing computational tractability.

What would settle it

An answer set program with weighted rules for which the derived distribution over models fails to match the log-linear form or for which no stable models can be enumerated in polynomial time relative to the unweighted case.

read the original abstract

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper sketches weighted rules for stable models to add probabilities and handle inconsistencies, but the abstract alone leaves the actual semantics and proofs uncheckable.

read the letter

The core idea is to lift log-linear weighting from Markov Logic into answer set programs so that rules can carry weights, letting the semantics rank models, assign probabilities, and perhaps do statistical inference over them. That direction is not entirely new in spirit, but applying it specifically inside stable model semantics and then comparing the result to ASP, MLN, ProbLog, and P-log is the concrete step the authors take. The comparison section is the part that could be immediately useful to someone already working in hybrid logical-probabilistic KR, because it at least tries to locate the proposal relative to the main existing formalisms. Beyond that, the abstract lists four applications—resolving inconsistencies, ranking models, associating probabilities, and statistical inference—but supplies no definitions, no example programs, and no proof sketches, so it is impossible to tell whether the weighting preserves the stable-model fixed-point property or whether the induced distribution stays well-defined when the program is inconsistent. The central assumption that weights can be added without breaking tractability or introducing hidden circularity therefore remains untested in the material available. This work is aimed at researchers who already know answer-set programming and want to see how probabilistic extensions might look inside that framework rather than in a separate probabilistic logic. A reader in that narrow group could extract some value from the positioning against ProbLog and P-log, but the paper would need the missing formal parts before it could be used as a foundation for further work. I would send it to peer review so that referees can check whether the weighting mechanism actually delivers the claimed capabilities without side effects; the idea is worth a careful look even if the current version is only a sketch.

Referee Report

2 major / 0 minor

Summary. The paper introduces weighted rules under the stable model semantics, modeled after the log-linear approach in Markov Logic. It claims this extension overcomes the deterministic limitations of standard answer set programming by enabling inconsistency resolution in ASP, ranking of stable models, probability assignment to models, and statistical inference over weighted stable models. The work also includes formal comparisons to answer set programs, Markov Logic, ProbLog, and P-log.

Significance. If the proposed weighting integrates cleanly with stable model semantics while preserving key properties such as minimality and supporting the listed probabilistic applications, the result would offer a useful bridge between logic programming and statistical relational models. The explicit comparisons to related formalisms are a positive feature that helps situate the contribution.

major comments (2)

[Abstract] Abstract: the central claim that weighted rules 'resolve inconsistencies in answer set programs' and 'associate probability to stable models' lacks any supporting definition, example, or proof in the manuscript. Without the formal semantics (e.g., how weights modify the reduct or the probability distribution over answer sets), it is impossible to verify whether the construction avoids contradictions or preserves computational properties.
No formal definition section: the manuscript provides no equations or inductive definition for the weighted stable model semantics, nor any statement of the probability measure over models. This is load-bearing for all four claimed applications (inconsistency resolution, ranking, probability association, and inference).

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive report. The comments correctly identify that the abstract and presentation of the core definitions require strengthening to make the claims self-contained and verifiable. We will revise the manuscript to address these points directly while preserving the existing comparisons to related formalisms.

read point-by-point responses

Referee: [Abstract] Abstract: the central claim that weighted rules 'resolve inconsistencies in answer set programs' and 'associate probability to stable models' lacks any supporting definition, example, or proof in the manuscript. Without the formal semantics (e.g., how weights modify the reduct or the probability distribution over answer sets), it is impossible to verify whether the construction avoids contradictions or preserves computational properties.

Authors: We agree that the abstract is too concise and does not contain definitions or examples. The body of the paper defines weighted stable models by extending the standard reduct construction with a log-linear weighting function over satisfied rules and defines the probability of an answer set I as P(I) = (1/Z) * exp(sum of weights of rules satisfied by I). We will expand the abstract with a one-sentence description of this semantics and a short illustrative example showing both inconsistency resolution and probability assignment. This revision will make the central claims verifiable without requiring the reader to reach the main text. revision: yes
Referee: [—] No formal definition section: the manuscript provides no equations or inductive definition for the weighted stable model semantics, nor any statement of the probability measure over models. This is load-bearing for all four claimed applications (inconsistency resolution, ranking, probability association, and inference).

Authors: The manuscript contains the definition of weighted stable models (including the weighted reduct and the probability measure) in the section following the introduction, together with the four applications. However, we accept that the presentation would benefit from a dedicated, prominently labeled formal-definition subsection that isolates the inductive definition, the probability measure, and the normalization constant Z. We will add this subsection, include the explicit equations, and provide a brief proof sketch for each of the four applications. The comparisons to ASP, Markov Logic, ProbLog, and P-log will remain unchanged. revision: yes

Circularity Check

0 steps flagged

No significant circularity; proposal is self-contained

full rationale

The paper introduces weighted rules under stable model semantics by explicit analogy to external log-linear models from Markov Logic, then defines methods for ranking, probability association, and inference. No equations or definitions are shown reducing to fitted parameters, self-citations, or prior results by the same authors. Formal comparisons with ASP, ProbLog, and P-log are presented as external benchmarks rather than internal derivations. The central construction therefore does not collapse to its own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Based solely on the abstract, no specific free parameters, axioms, or invented entities are identifiable; the work appears to extend existing semantics rather than introduce new fitted constants or entities.

pith-pipeline@v0.9.0 · 5355 in / 1023 out tokens · 56838 ms · 2026-05-12T03:31:39.335517+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

We introduce the concept of weighted rules under the stable model semantics following the log-linear models of Markov Logic... WΠ(I) = exp(∑ w:R∈ΠI w) if I∈SM[Π]
IndisputableMonolith/Foundation/AbsoluteFloorClosure.lean absolute_floor_iff_bare_distinguishability unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

Theorem 3: For any tight LPMLN program Π... Comp(Π) and Π have the same probability distribution

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

300 extracted references · 300 canonical work pages · 10 internal anchors

[1]

Balduccini, M., and Gelfond, M. 2003. Logic programs with consistency-restoring rules. In International Symposium on Logical Formalization of Commonsense Reasoning, AAAI 2003 Spring Symposium Series , 9--18

work page 2003
[2]

Baral, C.; Gelfond, M.; and Rushton, J. N. 2009. Probabilistic reasoning with answer sets. TPLP 9(1):57--144

work page 2009
[3]

Bauters, K.; Schockaert, S.; De Cock, M.; and Vermeir, D. 2010. Possibilistic answer set programming revisited. In 26th Conference on Uncertainty in Artificial Intelligence (UAI 2010)

work page 2010
[4]

Buccafurri, F.; Leone, N.; and Rullo, P. 2000. Enhancing disjunctive datalog by constraints. Knowledge and Data Engineering, IEEE Transactions on 12(5):845--860

work page 2000
[5]

De Raedt, L.; Kimmig, A.; and Toivonen, H. 2007. P rob L og: A probabilistic prolog and its application in link discovery. In IJCAI , volume 7, 2462--2467

work page 2007
[6]

Denecker, M., and Ternovska, E. 2007. Inductive situation calculus. Artificial Intelligence 171(5-6):332--360

work page 2007
[7]

Erdem, E., and Lifschitz, V. 2003. Tight logic programs. TPLP 3:499--518

work page 2003
[8]

Fierens, D.; Van den Broeck, G.; Renkens, J.; Shterionov, D.; Gutmann, B.; Thon, I.; Janssens, G.; and De Raedt, L. 2015. Inference and learning in probabilistic logic programs using weighted boolean formulas. TPLP 15(03):358--401

work page 2015
[9]

Gelfond, M., and Lifschitz, V. 1988. The stable model semantics for logic programming. In Kowalski, R., and Bowen, K., eds., Proceedings of International Logic Programming Conference and Symposium , 1070--1080. MIT Press

work page 1988
[10]

Gutmann, B. 2011. On Continuous Distributions and Parameter Estimation in Probabilistic Logic Programs . Ph.D. Dissertation, KU Leuven

work page 2011
[11]

Lee, J., and Lifschitz, V. 2003. Loop formulas for disjunctive logic programs. In Proceedings of International Conference on Logic Programming ( ICLP ) , 451--465

work page 2003
[12]

Lee, J., and Wang, Y. 2015. A probabilistic extension of the stable model semantics. In International Symposium on Logical Formalization of Commonsense Reasoning, AAAI 2015 Spring Symposium Series

work page 2015
[13]

Lee, J.; Meng, Y.; and Wang, Y. 2015. Markov logic style weighted rules under the stable model semantics. In Technical Communications of the 31st International Conference on Logic Programming

work page 2015
[14]

Lin, F., and Zhao, Y. 2004. A S S A T : Computing answer sets of a logic program by S A T solvers. Artificial Intelligence 157:115--137

work page 2004
[15]

Nickles, M., and Mileo, A. 2014. Probabilistic inductive logic programming based on answer set programming. In 15th International Workshop on Non-Monotonic Reasoning (NMR 2014)

work page 2014
[16]

Niepert, M.; Noessner, J.; and Stuckenschmidt, H. 2011. Log-linear description logics. In IJCAI , 2153--2158

work page 2011
[17]

Poole, D. 1997. The independent choice logic for modelling multiple agents under uncertainty. Artificial Intelligence 94:7--56

work page 1997
[18]

Richardson, M., and Domingos, P. 2006. Markov logic networks. Machine Learning 62(1-2):107--136

work page 2006
[19]

Sato, T. 1995. A statistical learning method for logic programs with distribution semantics. In Proceedings of the 12th International Conference on Logic Programming (ICLP) , 715--729

work page 1995
[20]

Vennekens, J.; Verbaeten, S.; Bruynooghe, M.; and A, C. 2004. Logic programs with annotated disjunctions. In Proceedings of International Conference on Logic Programming (ICLP) , 431--445

work page 2004
[21]

Vennekens, J.; Denecker, M.; and Bruynooghe, M. 2009. CP -logic: A language of causal probabilistic events and its relation to logic programming. TPLP 9(3):245--308

work page 2009
[22]

Transactions on Machine Learning Research , year=

A systematic evaluation of the planning and scheduling abilities of the reasoning model o1 , author=. Transactions on Machine Learning Research , year=

work page
[23]

doi: 10.18653/v1/2023.findings-emnlp.248

Pan, Liangming and Albalak, Alon and Wang, Xinyi and Wang, William. Logic- LM : Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023. doi:10.18653/v1/2023.findings-emnlp.248

work page doi:10.18653/v1/2023.findings-emnlp.248 2023
[24]

Advances in Neural Information Processing Systems , volume=

Boardgameqa: A dataset for natural language reasoning with contradictory information , author=. Advances in Neural Information Processing Systems , volume=

work page
[25]

M ulti L ogic NMR (er): A Benchmark and Neural-Symbolic Framework for Non-monotonic Reasoning with Multiple Extensions

Xiu, Yeliang and Liu, Yongmei. M ulti L ogic NMR (er): A Benchmark and Neural-Symbolic Framework for Non-monotonic Reasoning with Multiple Extensions. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025. doi:10.18653/v1/2025.emnlp-main.927

work page doi:10.18653/v1/2025.emnlp-main.927 2025
[26]

Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools

Hao, Yilun and Chen, Yongchao and Zhang, Yang and Fan, Chuchu. Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025. doi:10.18653/v1/...

work page doi:10.18653/v1/2025.naacl-long.176 2025
[27]

Exploring

Chatziveroglou, Giannis and Yun, Richard and Kelleher, Maura , journal=. Exploring

work page
[28]

Hengle, Amey and Bajpai, Prasoon and Dan, Soham and Chakraborty, Tanmoy , journal=. Can

work page
[29]

Advances in Neural Information Processing Systems , volume=

Babilong: Testing the limits of llms with long context reasoning-in-a-haystack , author=. Advances in Neural Information Processing Systems , volume=

work page
[30]

CoRR , year=

Long-context LLMs Struggle with Long In-context Learning , author=. CoRR , year=

work page
[31]

2025 , month =

Context Rot: How Increasing Input Tokens Impacts LLM Performance , author =. 2025 , month =

work page 2025
[32]

arXiv preprint arXiv:2506.08625 , year=

RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval , author=. arXiv preprint arXiv:2506.08625 , year=

work page arXiv
[33]

Advances in Neural Information Processing Systems , volume=

Language models can solve computer tasks , author=. Advances in Neural Information Processing Systems , volume=

work page
[34]

Advances in Neural Information Processing Systems , volume=

Reflexion: Language agents with verbal reinforcement learning , author=. Advances in Neural Information Processing Systems , volume=

work page
[35]

Advances in Neural Information Processing Systems , volume=

Self-refine: Iterative refinement with self-feedback , author=. Advances in Neural Information Processing Systems , volume=

work page
[36]

Chain-of-Verification Reduces Hallucination in Large Language Models

Dhuliawala, Shehzaad and Komeili, Mojtaba and Xu, Jing and Raileanu, Roberta and Li, Xian and Celikyilmaz, Asli and Weston, Jason. Chain-of-Verification Reduces Hallucination in Large Language Models. Findings of the Association for Computational Linguistics: ACL 2024. 2024. doi:10.18653/v1/2024.findings-acl.212

work page doi:10.18653/v1/2024.findings-acl.212 2024
[37]

CoRR , year=

Internal Consistency and Self-Feedback in Large Language Models: A Survey , author=. CoRR , year=

work page
[38]

AI solves IMO problems at silver medal level , year =

work page
[39]

Nature , volume=

DeepMind AI crushes tough maths problems on par with top human solvers , author=. Nature , volume=. 2025 , publisher=

work page 2025
[40]

Ishay, Adam and Lee, Joohyung , booktitle=

work page
[41]

Kalyanpur, Aditya and Saravanakumar, Kailash and Barres, Victor and Chu-Carroll, Jennifer and Melville, David and Ferrucci, David A , journal=

work page
[42]

CoRR , year=

RULER: What's the Real Context Size of Your Long-Context Language Models? , author=. CoRR , year=

work page
[43]

CoRR , year=

NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes , author=. CoRR , year=

work page
[44]

0 (2019) , author=

Potassco User Guide, Version 2.2. 0 (2019) , author=. URL https://github. com/potassco/guide/releases , year=

work page 2019
[45]

py: Bridging the Gap between LLMs and Constraint Solvers , author=

Logic. py: Bridging the Gap between LLMs and Constraint Solvers , author=. CoRR , year=

work page
[46]

2025 , editor =

Lin, Bill Yuchen and Le Bras, Ronan and Richardson, Kyle and Sabharwal, Ashish and Poovendran, Radha and Clark, Peter and Choi, Yejin , booktitle =. 2025 , editor =

work page 2025
[47]

Bill Yuchen Lin and Ronan Le Bras and Kyle Richardson and Ashish Sabharwal and Radha Poovendran and Peter Clark and Yejin Choi , booktitle =

work page
[48]

Proceedings of the 41st International Conference on Machine Learning , pages=

Position: LLMs can't plan, but can help planning in LLM-modulo frameworks , author=. Proceedings of the 41st International Conference on Machine Learning , pages=

work page
[49]

arXiv preprint arXiv:2406.03367 , year=

CLMASP: Coupling Large Language Models with Answer Set Programming for Robotic Task Planning , author=. arXiv preprint arXiv:2406.03367 , year=

work page arXiv
[50]

2025 , URL =

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity , author =. 2025 , URL =

work page 2025
[51]

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

The illusion of thinking: Understanding the strengths and limitations of reasoning models via the lens of problem complexity , author=. arXiv preprint arXiv:2506.06941 , year=

work page internal anchor Pith review arXiv
[52]

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Stop overthinking: A survey on efficient reasoning for large language models , author=. arXiv preprint arXiv:2503.16419 , year=

work page internal anchor Pith review arXiv
[53]

Do not think that much for 2+ 3=? on the overthinking of o1-like

Chen, Xingyu and Xu, Jiahao and Liang, Tian and He, Zhiwei and Pang, Jianhui and Yu, Dian and Song, Linfeng and Liu, Qiuzhi and Zhou, Mengfei and Zhang, Zhuosheng and others , journal=. Do not think that much for 2+ 3=? on the overthinking of o1-like

work page
[54]

Reasoning Models Don't Always Say What They Think

Reasoning Models Don't Always Say What They Think , author=. arXiv preprint arXiv:2505.05410 , year=

work page internal anchor Pith review arXiv
[55]

CoRR , volume =

Beyond semantics: The unreasonable effectiveness of reasonless intermediate tokens , author=. arXiv preprint arXiv:2505.13775 , year=

work page arXiv
[56]

2025 , note =

Kavukcuoglu, Koray , title =. 2025 , note =

work page 2025
[57]

Introducing O3 and O4 Mini , year =

work page
[58]

OpenAI o1 System Card

Openai o1 system card , author=. arXiv preprint arXiv:2412.16720 , year=

work page internal anchor Pith review Pith/arXiv arXiv
[59]

Deepseek-r1: Incentivizing reasoning capability in

Guo, Daya and Yang, Dejian and Zhang, Haowei and Song, Junxiao and Zhang, Ruoyu and Xu, Runxin and Zhu, Qihao and Ma, Shirong and Wang, Peiyi and Bi, Xiao and others , journal=. Deepseek-r1: Incentivizing reasoning capability in

work page
[60]

Balachandran, J

Inference-time scaling for complex tasks: Where we stand and what lies ahead , author=. arXiv preprint arXiv:2504.00294 , year=

work page arXiv
[61]

Sudoku-bench: Evaluating creative reasoning with sudoku variants

Sudoku-Bench: Evaluating creative reasoning with Sudoku variants , author=. arXiv preprint arXiv:2505.16135 , year=

work page arXiv
[62]

2024 , url =

OpenAI , title =. 2024 , url =

work page 2024
[63]

On the self-verification limitations of large language models on reasoning and planning tasks

On the self-verification limitations of large language models on reasoning and planning tasks , author=. arXiv preprint arXiv:2402.08115 , year=

work page arXiv
[64]

When can LLMs actually correct their own mistakes? A survey of self-correction

Kamoi, Ryo and Zhang, Yusen and Zhang, Nan and Han, Jiawei and Zhang, Rui. When Can LLM s Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLM s. Transactions of the Association for Computational Linguistics. 2024. doi:10.1162/tacl_a_00713

work page doi:10.1162/tacl_a_00713 2024
[65]

arXiv preprint arXiv:2410.02162 , year=

Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1 , author=. arXiv preprint arXiv:2410.02162 , year=

work page arXiv
[66]

Gemini: A Family of Highly Capable Multimodal Models

Gemini: a family of highly capable multimodal models , author=. arXiv preprint arXiv:2312.11805 , year=

work page internal anchor Pith review Pith/arXiv arXiv
[67]

The Claude 3 Model Family: Opus, Sonnet, Haiku , author=

work page
[68]

GPT-4 Technical Report

Gpt-4 technical report , author=. arXiv preprint arXiv:2303.08774 , year=

work page internal anchor Pith review Pith/arXiv arXiv
[69]

2023 , organization=

Gao, Luyu and Madaan, Aman and Zhou, Shuyan and Alon, Uri and Liu, Pengfei and Yang, Yiming and Callan, Jamie and Neubig, Graham , booktitle=. 2023 , organization=

work page 2023
[70]

The Eleventh International Conference on Learning Representations , year =

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language , author=. The Eleventh International Conference on Learning Representations , year =

work page
[71]

Common sense , volume=

Elaboration tolerance , author=. Common sense , volume=

work page
[72]

Advances in neural information processing systems , volume=

Large language models are zero-shot reasoners , author=. Advances in neural information processing systems , volume=

work page
[73]

2023 , month =

Ishay, Adam and Yang, Zhun and Lee, Joohyung , booktitle =. 2023 , month =. doi:10.24963/kr.2023/37 , url =

work page doi:10.24963/kr.2023/37 2023
[74]

Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text

Yang, Zhun and Ishay, Adam and Lee, Joohyung. Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text. Findings of the Association for Computational Linguistics: ACL 2023. 2023

work page 2023
[75]

Generalized planning in pddl domains with pretrained large language models,

Generalized Planning in PDDL Domains with Pretrained Large Language Models , author=. arXiv preprint arXiv:2305.11014 , year=

work page arXiv
[76]

Large Language Models Still Can't Plan (A Benchmark for

Karthik Valmeekam and Alberto Olmo and Sarath Sreedharan and Subbarao Kambhampati , booktitle=. Large Language Models Still Can't Plan (A Benchmark for. 2022 , url=

work page 2022
[77]

Conference on robot learning , pages=

Do as i can, not as i say: Grounding language in robotic affordances , author=. Conference on robot learning , pages=. 2023 , organization=

work page 2023
[78]

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Do as i can, not as i say: Grounding language in robotic affordances , author=. arXiv preprint arXiv:2204.01691 , year=

work page internal anchor Pith review Pith/arXiv arXiv
[79]

Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks , author=. arXiv preprint arXiv:2211.12588 , year=

work page internal anchor Pith review arXiv
[80]

Faithful Chain-of-Thought Reasoning , author=. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

work page

Showing first 80 references.