Papers with cross-model
Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models (2024.findings-acl)
Copied to clipboard
Zhuoran Jin, Pengfei Cao, Hongbang Yuan, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao
| Challenge: | Existing methods to expand internal memory boundaries of language models by providing external context can often conflict, leading to knowledge conflicts. |
| Approach: | They propose a method that prunes conflicting attention heads without updating model parameters. |
| Outcome: | The proposed method can flexibly control eight LMs to use internal memory or external context without updating model parameters. |
Explaining Generalization of AI-Generated Text Detectors Through Linguistic Analysis (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing studies have reported generalization gaps in AI-text detectors, but they lack insights into the causes. |
| Approach: | They propose to analyze generalization behavior of AI-text detectors using linguistic analysis to explain performance variance. |
| Outcome: | The proposed model can generalize across unseen prompts, model families, and domains, but it can't generalize under distribution shifts. |
Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent efforts have identified adversarial suffixes capable of jailbreaking LLMs . however, GCG struggles with computational inefficiency, limiting further studies . |
| Approach: | They propose a two-stage transfer learning framework which decouples the search process into behavior-agnostic pre-searching and behavior-relevant post-search. |
| Outcome: | The proposed approach outperforms baseline on Llama2-chat-7b with ASRs of 43.9 (+ 22.2) and 39.0 (+ 19.5) on valid and test sets. |
Verifiable LLM-Generated Text Detection via Projected Semantic-Structural Distributions (2026.acl-long)
Copied to clipboard
Ruochong Xiong, Qien Li, Wangwang Lian, Yulong Wan, Hanlin Xue, Zhouxing Tan, Han Yang, Fengyu Lu, Junfei Liu
| Challenge: | Existing methods for detecting LLM-Generated text suffer from distribution misalignment and limited interpretability. |
| Approach: | They propose a statistical framework utilizing supervised subspace learning to extract compact features and construct conditional semantic distributions based on syntactic structures. |
| Outcome: | The proposed framework is superior in cross-domain, cross-model, and adversarial scenarios. |
SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for hallucination detection rely on self-consistency check alone . prominent LMs exhibit a tendency to produce exceedingly confident, but erroneous, assertions . |
| Approach: | They propose a sampling-based method that expands on the principle of self-consistency checking to detect hallucinations at question-level and model-level. |
| Outcome: | The proposed method outperforms the state of the art in detecting non-factual and factual statements across multiple question-answering and open-domain generation benchmarks. |
Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing red-team methods rely on modifying user prompts, which lack adaptability to new data and may impact the agent’s performance. |
| Approach: | They propose a framework that implicitly manipulates the agent’s reasoning trajectory and memory retrieval with three key stages: Trigger Extraction, Reasoning Hijacking, and Constraint Tightening. |
| Outcome: | The proposed framework shows outstanding performance in cross-model and cross-scenario environments. |