across-14-models-syllogisms-posed-symbolic-form-solved-far CLM-0287observationsingle paperReviewed by AI
Across 14 models, syllogisms posed in symbolic form are solved far better than the same inferences in natural language: top models reach near-perfect symbolic accuracy (about 99.6%) while scoring around chance (52%) on the natural-language understanding variant, mean 81.7% versus 56% overall, and few-shot prompting did not help, so formal-pattern competence does not carry over to reading the logic out of ordinary sentences.
Capability: Deducing validly from logical structure
Observed on
14 LLMs, syllogism dataset in symbolic and natural-language forms, zero-, few-shot and CoT prompting, 2025..
Sources
- One dataset; the NL variant's difficulty could partly reflect ambiguity in phrasing. The size of the gap and the near-perfect symbolic scores are the notable parts.
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- Presenting syllogisms as Euler or linear diagrams instead of text or logical notation did not consistently improve two models' accuracy on 285 problems; both did well on entailment and contradiction items but poorly on neutral ones (GPT-4o-mini under 30% on neutral cases), and made systematic conversion errors, treating 'all A are B' as if it implied 'all B are A'.Deducing validly from logical structure · reviewed by AI
- For a domain-specific language essentially absent from pretraining corpora (FORM symbolic algebra), QLoRA fine-tuning an 8B model on a few thousand examples validated by executing them through the language's own interpreter beats frontier open-weight models of up to 756B parameters given syntax documentation in context, on execution rate and strict output match for the larger benchmarks, while general reasoning scores drop under 3 points.Generating and editing working code · reviewed by AI
- When an 8B model verifies natural-language claims against knowledge-graph triples, scoring the evidence twice under opposing prompts (argue it supports, argue it refutes) and adjudicating between the two arguments avoids the bias toward a "Supported" verdict that a single-perspective assessment shows, and is the largest single contributor to accuracy in that pipeline.Checking claims against evidence · reviewed by AI
- Models judge a syllogism's validity partly by how believable its conclusion is because validity and plausibility are encoded as linearly separable but strongly aligned directions in the residual stream: steering along the plausibility direction causally shifts validity judgements and vice versa, the degree of alignment predicts the size of the content effect across models, and a debiasing vector that separates the two reduces the effect and raises accuracy.Deducing validly from logical structure · reviewed by AI
- On text-to-SQL benchmarks, aggregate accuracy hides a steep difficulty gradient: pre-trained-language-model-based parsers resolved roughly 80% of Spider cases overall but only about 50% of its extra-hard cases, and as natural-language understanding improved the residual errors shifted toward database-side problems — large schemas, ambiguous columns, dirty cell values — rather than language parsing.Writing a reusable locator: regex, SQL, XPath · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: Frontier models scoring above 85% on the natural-language variant with the symbolic gap closed.