Guan Wang University of the Chinese Academy of Sciences and Institute of Information Engineering, Chinese Academy of Sciences, Biyu Zhou, Xuehai Tang, Jizhong Han Chinese Academy of Science, Songlin Hu
To address the increasingly severe safety risk of large language models (LLMs), reasoning-based safety alignment methods have emerged. These methods overcome the limitations of ’shallow alignment’ by exposing the model’s Chain-of-Thought (CoT), enabling auditability of safety reasoning process through both training-phase supervision and post-generation verification. However, this transparency creates a critical vulnerability, a tension we define as the Security Auditability Dilemma: while explicit reasoning is a prerequisite for safety, its textual Auditable paradoxically transforms it into an optimization target for adaptive attackers and induces the model to unintentionally copy harmful content from its own reasoning context. To address this, we propose Auditable Latent CoT Alignment (ALCA), a framework that decouples internal reasoning from external output. ALCA shifts the safety deliberation process into a continuous latent space. This allows the safety reasoning process to guide the generation of harmless outputs, while eliminates the discrete textual surface that facilitates internal copying and adaptive attack. Yet, this process is not a black box. we introduce a restricted Self-Decoding mechanism that allows the model to reconstruct its latent reasoning into human-readable text for supervision under specific guidance. Extensive experiments show that ALCA achieves robustness alignment, reducing the success rate of adaptive jailbreak attacks by over 40% compared to strong baselines, while preserving performance. Our framework presents a path toward building LLMs that are both robustly secure and auditable.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Guan Wang University of the Chinese Academy of Sciences and Institute of Information Engineering, Chinese Academy of Sciences, Xuehai Tang, Biyu Zhou, Jizhong Han Chinese Academy of Science, Songlin Hu
Prevailing safety alignment methods still leave Large Language Models (LLMs) vulnerable to sophisticated jailbreak attacks. To bolster defenses, explicit reasoning mechanisms like Safety-oriented Chain-of-Thought (SCoT) have emerged, significantly enhancing robustness. However, this transparency introduces a critical trade-off: the exposed reasoning process itself becomes a new attack surface, risking the leakage of harmful information and revealing the model’s safety logic to adversaries. This paper directly confronts this dilemma, asking: Can we achieve the full benefits of deliberative safety without the costs of explicit reasoning generation? We propose Safety Reasoning Internalization to make the deliberative process in SCoT “available but not visible”. This approach is grounded in a key theoretical insight: the corrective influence of an SCoT can be effectively approximated by a targeted, low-rank update to the model’s Feed-Forward Network (FFN) layers. We operationalize this through Hierarchical Internalization of Adversarially-Guided Reasoning (HIAR), a layer-wise safety alignment framework that internalizes safety reasoning into an implicit computational pathway using Low-Rank Adaptation (LoRA). HIAR enables the model to reach a safe conclusion within a single forward pass, entirely eliminating the need to generate vulnerable SCoT text. Extensive experiments on various LLMs demonstrate that HIAR achieves a 43% lower Attack Success Rate (ASR) against distinct jailbreak attacks compared to strong baselines.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Bingkang Shi, Jen-tse Huang, Luo Long, Tianyu Zong, Hongzhu Yi, Yuanxiang Wang University of the Chinese Academy of Sciences, Songlin Hu, Xiaodan Zhang 等 9 位作者
Large Language Models (LLMs) have increasingly enhanced or replaced traditional Non-Player Characters (NPCs) in video games. However, these LLM-based NPCs inherit underlying social biases (e.g., race or class), posing fairness risks during in-game interactions. To address the limited exploration of this issue, we introduce FairGamer, the first benchmark to evaluate social biases across three interaction patterns: transaction, cooperation, and competition. FairGamer assesses four bias types, including class, race, age, and nationality, across 12 distinct evaluation tasks using a novel metric, FairMCV. Our evaluation of seven frontier LLMs reveals that: (1) models exhibit biased decision-making, with Grok-4-Fast demonstrating the highest bias (average FairMCV = 76.9%); and (2) larger LLMs display more severe social biases, suggesting that increased model capacity inadvertently amplifies these biases. We release FairGamer at https://github.com/BingkangShi/FairGamer to facilitate future research on NPC fairness.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Dou Hu Communication University of China, Lingwei Wei Institute of Information Engineering, Chinese Academy of Sciences, Hongjiang Xiao Communication University of China, Songlin Hu, Yuan Zhang Communication University of China
Multi-task learning (MTL) enables joint learning over multiple tasks based on shared representations, but suffers from task interference issue during optimization. Existing works mainly focus on task balancing or probabilistic modeling but fail to address the issue since they struggle to learn sufficient representations for all target tasks. To address this, we propose a multi-task representation alignment (MTRA) framework to achieve task-specific alignment and self-alignment on the shared representations from a mutual information perspective. MTRA ensures that the learned representations contain task-relevant features while mitigating the negative effects of task-irrelevant features. First, we design a task-specific alignment objective to align the shared representations and task-specific representations with the expected targets of all tasks via information maximization. Besides, we design a self-alignment objective to eliminate task-irrelevant features via conditional information minimization. Experiments on two multi-task language benchmarks show that MTRA outperforms 13 representative MTL methods under the same settings, particularly under label-noisy and data-constrained conditions. Further analysis shows that the learned shared representations exhibit sufficient task informativeness and superior alignment properties.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yiting Shen, Kun Li Institute of Information Engineering, Chinese Academy of Sciences, Wei Zhou Institute of Information Engeering, Songlin Hu
Large Language Model (LLM)-based agents are increasingly deployed for complex, tool-based tasks where long-term memory is critical to driving actions. Existing benchmarks, however, primarily test an agent’s ability to passively retrieve isolated facts in response to explicit questions. They fail to evaluate the more crucial capability of actively applying memory to execute tasks. To address this gap, we introduce Mem2ActBench, a benchmark for evaluating whether agents can proactively leverage long-term memory to execute tool-based actions by selecting appropriate tools and grounding their parameters. The benchmark simulates persistent assistant usage, where users mention the same topic across long, interrupted interactions and expect previously established preferences and task states to be implicitly applied. We build the dataset with an automated pipeline that merges heterogeneous sources (ToolACE, BFCL, OASST1), resolves conflicts via consistency modeling, and synthesizes 2,029 sessions with 12 user–assistant–tool turns on average. From these memory chains, a reverse-generation method produces 400 tool-use tasks, with human evaluation confirming 91.3% are strongly memory-dependent. Experiments on seven memory frameworks show that current systems remain inadequate at actively utilizing memory for parameter grounding, highlighting the need for more effective approaches to evaluate and improve memory application in task execution. Code and data are available at https://github.com/Cantaloupe-M/Mem2ActBench.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表