QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA (2025.findings-emnlp)
Copied to clipboard
Jacob Dineen, Aswin Rrv, Qin Liu, Zhikun Xu, Xiao Ye, Ming Shen, Zhaonan Li, Shijie Lu, Chitta Baral, Muhao Chen, Ben Zhou
| Challenge: | QA-LIGN decomposes monolithic rewards into interpretable principle-specific evaluations . scalar rewards obscure which objectives drive the training signal . |
| Approach: | a new method decomposes monolithic rewards into interpretable principle-specific evaluations . QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate . |
| Outcome: | QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate . the results outperform DPO and GRPO with state-of-the-art reward models given equivalent training . |
Similar Papers
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training (2026.findings-acl)
Copied to clipboard
Rui Zhang, Hongwei Li, Yun Shen, Xinyue Shen, Wenbo Jiang, Guowen Xu, Yang Liu, Michael Backes, Yang Zhang
| Challenge: | Misaligned large language models can magnify harm by exploiting them to undermine safety . et al., 2022b; Bai e.t., 2023): misalignment, realignment and model-specific resistance are important . |
| Approach: | They evaluate four methods to identify a mechanism asymmetry between attack and defense . they find that ORPO is most effective for misalignment, but DPO excels in realignment . |
| Outcome: | The proposed methods show a mechanism asymmetry between attack and defense . the proposed methods excel in realignment, but at the expense of model utility . |
Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety (2026.eacl-srw)
Copied to clipboard
Denis Janiak, Julia Moska, Dawid Motyka, Karolina Seweryn, Paweł Walkowiak, Bartosz Żuk, Arkadiusz Janz
| Challenge: | Existing studies focus on individual techniques or specific dimensions, lacking a holistic assessment of the inherent trade-offs. |
| Approach: | They propose a framework that compares LLM alignment methods across five axes . they use a validated LLM-as-judge prompt to compare the results . |
| Outcome: | The proposed framework compares LLM alignment methods across factuality, safety, conciseness, proactivity, diversity and safety axes . it provides insights into trade-offs of common alignment methods, guiding the development of more balanced and reliable LLMs. |
PURE: Aligning LLM via Pluggable Query Reformulation for Enhanced Helpfulness (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) depend on vast amounts of text data sourced from the Internet for their training. |
| Approach: | They propose a new alignment paradigm that reformulates risky queries into highly relevant yet harmless ones before feeding them into LLMs. |
| Outcome: | The proposed approach eliminates the high costs of training base LLMs and achieves a promising balance of harmlessness and helpfulness. |
Aligning Large Language Models via Fine-grained Supervision (2024.acl-short)
Copied to clipboard
| Challenge: | Pre-trained large-scale language models often generate biased or toxic text, misaligning with human intentions. |
| Approach: | They propose to use human feedback to improve LLM alignment by fine-grained token supervision . they ask annotators to edit less preferred responses to make them more favorable . |
| Outcome: | The proposed method improves LLM alignment by up to 5.1% in terms of win rate compared with the traditional model. |
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) excel in natural language processing tasks but are vulnerable to harmful content and being exploited for malicious purposes. |
| Approach: | They propose a framework to measure the risk coverage of alignment datasets across three dimensions: Lexical Diversity, Malicious Intent, and Jailbreak Tactics. |
| Outcome: | The proposed framework measures risk coverage across Lexical Diversity, Malicious Intent, and Jailbreak Tactics. |
A Survey on Training-free Alignment of Large Language Models (2025.findings-emnlp)
Copied to clipboard
Birong Pan, Yongqi Li, Weiyu Zhang, Wenpeng Lu, Mayi Xu, Shen Zhou, Yuanyuan Zhu, Ming Zhong, Tieyun Qian
| Challenge: | a survey of large language models (LLMs) aims to ensure outputs adhere to human values, ethical standards, and legal norms. |
| Approach: | They present the first systematic review of TF alignment methods . they categorize them by stages of pre-decoding, in-decoder and post-decoration . |
| Outcome: | The proposed methods are based on training-free (TF) alignment techniques . they are able to be used in open-source and closed-source environments without retraining . |
Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Empirical evaluations on eight recent LLMs reveal that DRPO significantly enhances alignment performance, enabling base models to outperform their SFT/RLHF-tuned counterparts. |
| Approach: | They propose a tuning-free approach to self-alignment called Dynamic Rewarding with Prompt Optimization (DRPO) it leverages a dynamic rewarding mechanism to identify and rectify alignment weaknesses . |
| Outcome: | The proposed approach outperforms existing methods and is highly adaptable to various alignment challenges. |
You Only Need One Single Token to Refine Safety Alignment (2026.findings-acl)
Copied to clipboard
| Challenge: | Excessive safety can lead to over-refusal, where models reject harmful-looking yet benign queries, severely limiting utility. |
| Approach: | They propose a lightweight training-based approach that reshapes the distributions of harmful and benign samples within the model’s decision space by using a single-token prefix. |
| Outcome: | The proposed approach can distinguish between harmful and benign samples while keeping the model frozen. |
Verifying the Subjective: Structured Multilingual Rewards for Low-Resource Alignment (2026.findings-acl)
Copied to clipboard
| Challenge: | Structured Multilingual Reward Modeling Framework extends Reinforcement Learning with Verifiable Rewards (RLVR) to subjective and open-ended tasks. |
| Approach: | They propose a framework that extends Reinforcement Learning with Verifiable Rewards to subjective and open-ended tasks. |
| Outcome: | The proposed framework improves reasoning capability and response quality on 7 tasks across 50 low-resource languages. |
On the Vulnerability of Safety Alignment in Open-Access LLMs (2024.findings-acl)
Copied to clipboard
Jingwei Yi, Rui Ye, Qisi Chen, Bin Zhu, Siheng Chen, Defu Lian, Guangzhong Sun, Xing Xie, Fangzhao Wu
| Challenge: | Large language models (LLMs) are susceptible to malicious exploitation, but are often rejected and limited harmfulness is limited. |
| Approach: | They propose two types of reverse alignment techniques: reverse supervised fine-tuning (RSFT) and reverse preference optimization (RPO). |
| Outcome: | The proposed methods can significantly enhance the success rate and harmfulness of jailbreak attacks, but they face high rejection rates and limited harmfulness. |