BiasFilter filters low-fairness segments during LLM generation using a reward model trained on a GPT-4-scored preference dataset, cutting bias on CEB and FairMT.
First the worst: Finding better gender translations during beam search
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Neural machine translation inference procedures like beam search generate the most likely output under the model. This can exacerbate any demographic biases exhibited by the model. We focus on gender bias resulting from systematic errors in grammatical gender translation, which can lead to human referents being misrepresented or misgendered. Most approaches to this problem adjust the training data or the model. By contrast, we experiment with simply adjusting the inference procedure. We experiment with reranking nbest lists using gender features obtained automatically from the source sentence, and applying gender constraints while decoding to improve nbest list gender diversity. We find that a combination of these techniques allows large gains in WinoMT accuracy without requiring additional bilingual data or an additional NMT model.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
BiasFilter: An Inference-Time Debiasing Framework for Large Language Models
BiasFilter filters low-fairness segments during LLM generation using a reward model trained on a GPT-4-scored preference dataset, cutting bias on CEB and FairMT.