Web This site Trusted
30 result(s) for “date 2020 site does lanyingim com site h1bdata info site bias in site draft css org site:arxiv.org” of 60 matched · 640 ms
Scope: Nishi’s own index (our crawl + Common Crawl) — not the whole live web. Some sites block all automated crawlers (anti-bot walls), so their pages may be absent here even though we never filter lawful content.
Freshness: no result on this page carries a fetch time yet (indexed before the fetch epoch was stored beside the doc)
This paper addresses three primary and two secondary research questions:
•
RQ1 (Output Quality): Does using PAWNI-generated structured prompts result in LLM outputs that are more complete and comprehensive compared to outputs from iterative naive prompting
from the top result below
https://arxiv.org/html/2608.01366v2
5 Automated Prompt Optimisation and Built-in Query Rewriting
3 Contributions: Prompt Elements and Task Taxonomy
3
https://arxiv.org/list/cs.CL/new
LG)
Half a million cuneiform clay tablets survive in museums worldwide, yet modern users can neither read nor write in the world's oldest writing system, leaving a 4,000-year cultural barrier that existing NLP tools have only partially addressed
https://arxiv.org/html/2608.03703v1
4 The Loop Gain: Rebalancing Pressure in One Number
3 A Model of Preying on a Mechanical Rebalancer
3
https://arxiv.org/list/math/new
We show that in this case the optimal ratio is $\varepsilon_1^2\cdot\varepsilon_2^{-3/2}$
https://arxiv.org/list/cs.AI/new
In practice, many field descriptions remain ambiguous or incomplete, as much of the essential context (e
https://arxiv.org/html/2608.03153v1
ca \orgnameSimon Fraser University and Korea University
Abstract
When in the lifecycle does a large gender wage gap emerge
https://arxiv.org/html/2608.02941v1
92 percentage point comprehension deficit in Bangla yet maintain an identical 92
https://arxiv.org/html/2608.02909v1
Through simulations, we show that this approach recovers estimates close to the true values, even in relatively small samples, while the standard approach can produce substantial bias in practice
https://arxiv.org/list/econ/new
Through simulations, we show that this approach recovers estimates close to the true values, even in relatively small samples, while the standard approach can produce substantial bias in practice
https://arxiv.org/html/2608.02617v1
3 Response length: Verbosity bias in pairwise preference
https://arxiv.org/html/2608.02665v1
We ask a construct-validity question about this instrument and a reliability question about its noise: when an item’s intent is held fixed and only its meaning-preserving surface form varies, does the canonical-form score faithfully estimate model behavior, and how much of any variation is decoding/judge noise
https://arxiv.org/html/2608.02943v1
We then characterize the propagated bias from smoothing, establish validity of a full recursive residual bootstrap, and derive the additional covariance contribution from a finite number of simulated paths, providing bandwidth-free inference for the empirical-residual version of the same normal-rank response used in
https://arxiv.org/html/2608.00028v1
Abstract
A recurring question in the design of scalable multi-agent systems—from robot swarms to collectives of large-language-model (LLM) agents—is whether adding more agents can, on its own, overcome performance limits, or whether a qualitatively deeper organization is required
https://arxiv.org/html/2608.03577v1
This paper examines some fundamental limitations of the QE technology from both theoretical and empirical perspectives, arguing that current QE systems are structurally ill-equipped to serve as reliable standalone tools in real-world translation workflows
https://arxiv.org/html/2607.28847v1
1 Algorithmic Fairness in Management Science
2
https://arxiv.org/html/2608.02668v1
This view places Euclidean residual connections and GeoNorm in one framework
https://arxiv.org/html/2607.29281v2
This version is a work in progress; please feel free to contact me if you find a mistake, think I missed an important contribution, or just want to send a comment
https://arxiv.org/html/2604.05327v4
While a substantial literature studies local asymptotics under local misspecification, where misspecification typically manifests as an added bias in the Gaussian limit, our framework permits the Gaussian family itself to be globally misspecified in the limit experiment, thereby accommodating much richer classes of
https://arxiv.org/list/cs.CV/new
CV)
Recent advances in image generation have demonstrated the potential of unified multimodal models that integrate understanding, generation, and editing
https://arxiv.org/html/2608.03532v1
Abstract
Large language models are increasingly deployed in multilingual contexts, yet safety alignment and bias evaluation remain overwhelmingly English-centric
https://arxiv.org/html/2210.00131v4
For example, underspecification in Figure 1b may serve to amplify its gender-occupation shortcut bias relative to that of Figure 1a
https://arxiv.org/html/2608.02966v1
In conclusion, we show that incorrect answers carry distinct and useful measurement information rather than representing equivalent mistakes
https://arxiv.org/list/cs.IR/new
In a live A/B test on Shopee Homepage Search, it increases GMV per user by 1
https://arxiv.org/html/2608.03044v1
We call the first task emulation, in which models generate individual responses that aggregate into a population distribution
https://arxiv.org/list/q-fin/new
GN)
When in the lifecycle does a large gender wage gap emerge
https://arxiv.org/list/cs.CL/2025-06
5 family models trained in Portuguese
William Alberto Cruz-Castañeda, Marcellus Amadeus
Subjects: Computation and Language (cs
https://arxiv.org/html/2607.28127v1
Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs)
https://arxiv.org/list/q-fin.TR/new
6%, above zero and above the real lift in 100/100 seeds, indicating the placebo estimator is biased; we retain it as a bias diagnostic
https://arxiv.org/html/2608.03358v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/abs/astro-ph/0608636
Significant scale-dependent galaxy bias on large-scales, which changes with the r-band luminosity of the galaxies, could potentially explain differences in our Omega_m estimates and differences previously observed between 2dFGRS and SDSS power spectra and the resulting parameter constraints