◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Thong Bach

4 papers hereh-index 26 citations5 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author4

Across the 4 of 4 papers where every author was matched, so the position is known.

fields
  • cs.LG4

identity via Semantic Scholar / OpenAlex

collaborators

4 papers

cs.LG2026

Continual Safety Alignment via Gradient-Based Sample Selection

Thong Bach, Dung Nguyen, Thao Minh Le +1

Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, inc…

cs.LG2026

Guardrails in Logit Space: Safety Token Regularization for LLM Alignment

Thong Bach, Truyen Tran

Fine-tuning well-aligned large language models (LLMs) on new domains often degrades their safety alignment, even when using benign datasets. Existing safety alignment techniques pr…

cs.LG2025

Curvature-Aware Safety Restoration In LLMs Fine-Tuning

Thong Bach, Thanh Nguyen-Tang, Dung Nguyen +2

Fine-tuning Large Language Models (LLMs) for downstream tasks often compromises safety alignment, even when using parameter-efficient methods like LoRA. In this work, we uncover a…

cs.LG2025

Rethinking Deep Alignment Through The Lens Of Incomplete Learning

Thong Bach, Dung Nguyen, Thao Minh Le +1

Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-depend…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.