Query Timing Produces Opposite Positional Biases Between LLMs and Humans
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
Title:Query Timing Produces Opposite Positional Biases Between LLMs and Humans
Abstract:Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their evaluations remains poorly understood. Both primacy and recency biases have been observed in human judgments in response to evidence, but recent work suggest that \emph{when} the listener updates their beliefs -- during the presentation of evidence or only at the end -- influences the presence of such effects. We investigate whether a similar phenomenon holds for LLMs, finding divergence from human behavior. These biases are more exacerbated in newer models compared to their predecessors.
| Comments: | Entropic Award (Top 3 Paper), ICBINB @ ICLR 2026 |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2608.12387 [cs.CL] |
| (or arXiv:2608.12387v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.12387
arXiv-issued DOI via DataCite
|
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — NLP / Computation & Language
-
Geometric and Behavioral Stratification in Transformer Residual Streams
Aug 14
-
Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia
Aug 14
-
I-SDPO: Instance-Level Adaptive Self-Distillation Policy Optimization
Aug 14
-
Comment on "Modeling rapid language learning by distilling Bayesian priors into artificial neural networks"
Aug 14
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.