REVIEW 5 cited by
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
read the original abstract
Supervised fine-tuning (SFT) plays a crucial role in adapting large language models (LLMs) to specific domains or tasks. However, as demonstrated by empirical experiments, the collected data inevitably contains noise in practical applications, which poses significant challenges to model performance on downstream tasks. Therefore, there is an urgent need for a noise-robust SFT framework to enhance model capabilities in downstream tasks. To address this challenge, we introduce a robust SFT framework (RobustFT) that performs noise detection and relabeling on downstream task data. For noise identification, our approach employs a multi-expert collaborative system with inference-enhanced models to achieve superior noise detection. In the denoising phase, we utilize a context-enhanced strategy, which incorporates the most relevant and confident knowledge followed by careful assessment to generate reliable annotations. Additionally, we introduce an effective data selection mechanism based on response entropy, ensuring only high-quality samples are retained for fine-tuning. Extensive experiments conducted on multiple LLMs across five datasets demonstrate RobustFT's exceptional performance in noisy scenarios.
Forward citations
Cited by 5 Pith papers
-
Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching
Bidirectional LLM-GNN co-teaching with round-based pseudo-label preference optimization outperforms golden-teacher baselines on few-shot TAG benchmarks by 3-8% absolute gains.
-
Common-agency Games for Multi-Objective Test-Time Alignment
CAGE uses common-agency games and an EPEC algorithm to compute equilibrium policies that balance multiple conflicting objectives for test-time LLM alignment.
-
REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations
REALM learns per-annotator expertise scalars unsupervised by modeling each label as an expertise-weighted mixture of the model's prediction and a uniform random guess, delivering up to 50% accuracy gains over naive no...
-
REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations
REALM jointly learns model parameters and per-annotator expertise scalars during fine-tuning by modeling observed labels as mixtures of model predictions and uniform noise, improving accuracy under simulated annotation noise.
-
Analyzing the Effect of Noise in LLM Fine-tuning
Label noise hurts fine-tuning performance most while grammatical and typographical noise sometimes act as mild regularizers, with changes concentrated in task-specific layers.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.