Papers with cross-model

6 papers
Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models (2024.findings-acl)

Copied to clipboard

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations