← Back to all news
arXiv Machine Learning By Hanyu Yang

Less Loss, Fixed Weights: Logit Corrections for Forgetting

Read the original on arXiv Machine Learning →

The paper investigates whether a language model’s forgetting—worsening performance on standard web text after fine‑tuning or further pretraining—can be mitigated by simple, fixed adjustments to its final token predictions. By fitting a vocabulary‑wide bias (a token‑specific bonus or penalty) and optionally a temperature scaling, the authors evaluate recovery across 14 base‑to‑derived model pairs ranging from 1B to 7B parameters. Results show modest gains: up to 10% recovery with bias alone and up to 36% when combined with temperature, though models further pretrained on math lose the most and recover little; even in a controlled simulation with random damage, the bias‑plus‑temperature fix recovers 29%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computation and Language
Oct 9

Not Every Change Is Necessary: Recoverable Drift in Large Language Model Unlearning

The paper introduces Propose-Then-Project Unlearning (PTP-U), a method for large language model unlearning that first weakens target knowledge associations and then projects non-target outputs back to the original distribution to recover capabilities. PTP-U aims to satisfy forgetting constraints while preserving fluent generation and performance on non-target tasks. Experiments on three benchmarks show PTP-U achieves a strong forgetting‑retention trade‑off, with 81.22%–91.03% forgetting and an average of 94.20% non‑target utility.

By Xunlei Chen, Qinghui Gong, Jingkun Xue, Qihe Liu, Shijie Zhou, Fei Ye
llmsbenchmarks
More like this →
arXiv Computation and Language
Aug 25

CALIBURN: Self-Calibrated LLM Unlearning Alignment

CALIBURN is a new approach to large language model (LLM) unlearning that measures a model’s confidence in undesirable knowledge and uses this measure to fine‑tune unlearning gradient updates. By doing so, it offers more precise control over what is forgotten while better preserving the model’s overall utility. Experiments on benchmarks such as MUSE and WMDP show that CALIBURN outperforms existing methods in balancing knowledge removal with utility retention.

By Zhengbang Yang, Yisheng Zhong, Junyuan Hong, Zhuangdi Zhu
llmsbenchmarkssafety
More like this →
arXiv Computation and Language
2d ago

Unlearning by Extrapolating a Shrink-and-Heal Lookahead

The paper introduces SHIFT, a method for unlearning in large language models that avoids explicit forgetting targets by shrinking a fine‑tuned model toward its pre‑fine‑tuning weights and briefly relearning the retain set. In the linearized regime, this shrink‑and‑heal lookahead moves the model a fixed fraction toward the retrained model, and SHIFT extrapolates these per‑token changes into distillation targets for iterative refinement. Evaluated against eleven baselines under the OpenUnlearning protocol, SHIFT achieves the highest aggregate score across all TOFU settings, aligns 3.7× closer to the oracle than the next best method, and preserves the most retain knowledge on MUSE, maintaining proximity to the oracle even under larger optimization budgets and relearning attacks.

By Hoang-Chau Luong, Lingwei Chen
llmsfine-tuningefficiencysafety
More like this →