Commonsense reasoning S ≈ -2.15 uniform

Lower, uniform anchoring for pattern-matching tasks.

Source paper

extracted_from

(2025) · Edward Yi Chang · Kaya, Zeyneb N. · Ethan Chang

claim

community

Few-shot anchoring & latent structure
members_of
How minimal examples disambiguate and recruit latent arithmetic/reasoning interpretations in LLMs
Anchoring bias in commonsense reasoning
members_of
Studies how LMs exhibit uniform anchoring effects (S ≈ −2.15) across commonsense tasks, decomposed by cohesion, mismatch, and budget forces.
Commonsense reasoning anchoring bias
members_of
Uniform anchoring effect quantified at S ≈ −2.15 across commonsense reasoning tasks

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Commonsense reasoning tasks S≈-2.15finding0.861
Lower, more uniform anchoring for commonsense tasks
Commonsense reasoning shows uniform but weaker anchoring (S ≈ −2.15)finding0.844
Task-specific comparison.
Commonsense tasks show weaker but uniform anchoring on LLaMA (S ≈ −2.15)finding0.759
E3 finding suggesting pattern matching requires less intensive processing than compositional reasoning
common senseconcept0.748
The practical, reality-based judgment that guides successful unfolding and adaptation.
Compositional Reasoningconcept0.719
Modular reasoning enabled by monoid and other algebraic laws; central to maintainability and correctness of functional systems.
common sense informatic situationconcept0.706
The scenario where agents with different goals and knowledge interact, necessitating speech acts.
Compositional reasoning beyond Aristotle?question0.703
Secondary research question examining whether compositional frameworks can transcend classical logic.
double standard in inferring sentienceconcept0.701
Unequal willingness to attribute sentience to animals vs. plants despite similar behavioural evidence.