Evaluating Model Bias Requires Characterizing its Mistakes

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Albuquerque, Isabela, Schrouff, Jessica, Warde-Farley, David, Cemgil, Taylan, Gowal, Sven, Wiles, Olivia
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Evaluating Numerical Reasoning in Text-to-Image Models
par: Kajić, Ivana, et autres
Publié: (2024)

Benchmarking Diversity in Image Generation via Attribute-Conditional Human Evaluation
par: Albuquerque, Isabela, et autres
Publié: (2025)

Mind the Graph When Balancing Data for Fairness or Robustness
par: Schrouff, Jessica, et autres
Publié: (2024)

Dynamic Classifier-Free Diffusion Guidance via Online Feedback
par: Papalampidi, Pinelopi, et autres
Publié: (2025)

On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark
par: Fairoze, Jaiden, et autres
Publié: (2025)

Evaluating LLMs in Finance Requires Explicit Bias Consideration
par: Kong, Yaxuan, et autres
Publié: (2026)

FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
par: Aglietti, Virginia, et autres
Publié: (2024)

Learn from Your Mistakes: Self-Correcting Masked Diffusion Models
par: Schiff, Yair, et autres
Publié: (2026)

Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization
par: Polo, Felipe Maia, et autres
Publié: (2026)

Mistake-Bounded Language Generation
par: Kleinberg, Jon, et autres
Publié: (2026)

Optimal Mistake Bounds for Transductive Online Learning
par: Chase, Zachary, et autres
Publié: (2025)

Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning
par: Singh, Joykirat, et autres
Publié: (2024)

Mitigating LLM Hallucinations via Conformal Abstention
par: Yadkori, Yasin Abbasi, et autres
Publié: (2024)

AsymVLM: Asymmetric Token Pruning for Efficient Vision-Language Model Inference
par: Feng, Yilin, et autres
Publié: (2026)

Improving SAM Requires Rethinking its Optimization Formulation
par: Xie, Wanyun, et autres
Publié: (2024)

Generalizing to unseen domains via distribution matching
par: Albuquerque, Isabela, et autres
Publié: (2019)

AI Oversight and Human Mistakes: Evidence from Centre Court
par: Almog, David, et autres
Publié: (2024)

Distributionally Robust K-Means Clustering
par: Malik, Vikrant, et autres
Publié: (2026)

Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting
par: Feng, Yunzhen, et autres
Publié: (2025)

Evaluating Fairness in Transaction Fraud Models: Fairness Metrics, Bias Audits, and Challenges
par: Kamalaruban, Parameswaran, et autres
Publié: (2024)

On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
par: Agarwal, Rishabh, et autres
Publié: (2023)

Automatic Replication of LLM Mistakes in Medical Conversations
par: Proniakin, Oleksii, et autres
Publié: (2025)

Mistake-bounded online learning with operation caps
par: Geneson, Jesse, et autres
Publié: (2025)

Automatic Detection and Analysis of Singing Mistakes for Music Pedagogy
par: Kumar, Sumit, et autres
Publié: (2026)

Neural Compression of Atmospheric States
par: Mirowski, Piotr, et autres
Publié: (2024)

Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection
par: Han, Boyu, et autres
Publié: (2026)

Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis
par: Chen, Kai, et autres
Publié: (2023)

On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback
par: Faw, Matthew, et autres
Publié: (2025)

TIDES: Implicit Time-Awareness in Selective State Space Models
par: Soydan, Taylan, et autres
Publié: (2026)

On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective
par: Dmitriev, Daniil, et autres
Publié: (2024)

Evaluating AI systems under uncertain ground truth: a case study in dermatology
par: Stutz, David, et autres
Publié: (2023)

Bias in Large Language Models: Origin, Evaluation, and Mitigation
par: Guo, Yufei, et autres
Publié: (2024)

Fighting Sampling Bias: A Framework for Training and Evaluating Credit Scoring Models
par: Kozodoi, Nikita, et autres
Publié: (2024)

CEM: A Data-Efficient Method for Large Language Models to Continue Evolving From Mistakes
par: Zhao, Haokun, et autres
Publié: (2024)

Soft-prompt Tuning for Large Language Models to Evaluate Bias
par: Tian, Jacob-Junqi, et autres
Publié: (2023)

Mistake, Manipulation and Margin Guarantees in Online Strategic Classification
par: Shen, Lingqing, et autres
Publié: (2024)

Worst-Group Equalized Odds Regularization for Multi-Attribute Fair Medical Image Classification
par: Kurian, Nikhil Cherian, et autres
Publié: (2026)

Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning
par: Attias, Idan, et autres
Publié: (2025)

Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM-Based Evaluation
par: Tripathi, Tuhina, et autres
Publié: (2025)

Class-wise Autoencoders Measure Classification Difficulty And Detect Label Mistakes
par: Marks, Jacob, et autres
Publié: (2024)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
VUFIND_SESSION	"74cbe74f4ffa95a2e096cd3c146b3f49"
language	"fr"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790867572.8693 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "74cbe74f4ffa95a2e096cd3c146b3f49" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"VUFIND_SESSION=74cbe74f4ffa95a2e096cd3c146b3f49; language=fr; ui=standard"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.216.147"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"61559"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2407_10633/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2407_10633/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790867572.8638
REQUEST_TIME	1790867572

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler