Papers with SAGE

16 papers
SAGE: A Generic Framework for LLM Safety Evaluation (2025.emnlp-industry)

Copied to clipboard

Challenge: Current safety evaluation methodologies focus on single-turn interactions with generic policies, failing to capture conversational dynamics of real-world usage and application-specific harms.
Approach: They propose a framework for customized and dynamic harm evaluations that employs prompted adversarial agents with diverse personalities based on the Big Five model.
Outcome: The proposed framework enables system-aware multi-turn conversations that adapt to target applications and harm policies.
A Methodology for Generative Spelling Correction via Natural Spelling Errors Emulation across Multiple Domains and Languages (2024.findings-eacl)

Copied to clipboard

Challenge: Recent advances in large language models have shown impressive text generation and language understanding capabilities, evident in benchmarks like SuperGLUE, GEM, BigBench etc.
Approach: They propose a method for generative spelling correction that can be extended to any language with minor changes.
Outcome: The proposed method can be extended to any language with minor changes, and is based on a set of generative models with a single-domain and multi-domain test sets.
SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models (2026.eacl-industry)

Copied to clipboard

Challenge: Large language models (LLMs) have achieved remarkable progress, yet their internal mechanisms remain largely opaque.
Approach: They propose an agent-based framework that recasts feature interpretation from a passive, single-pass generation task into an explanation-driven process.
Outcome: The proposed framework produces explanations with significantly higher generative and predictive accuracy compared to state-of-the-art baselines.
SAGE: A Search-AuGmented Evaluation of Large Language Models on Free-Form QA (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are prone to hallucination and rely on static, pre-annotated references for evaluation.
Approach: They propose a framework to assess large language models without fixed ground-truth answers by iteratively generating web queries and synthesizing external evidence.
Outcome: The proposed framework achieves substantial to perfect agreement with human evaluations on multiple free-form QA benchmarks.
Reinforcement Learning for Self-Improving Agent with Skill Library (2026.acl-long)

Copied to clipboard

Challenge: Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions but struggle to continuously improve and adapt when deployed in new environments.
Approach: They propose a Reinforcement Learning-based approach to enhance agents’ self-improvement capabilities with a skill library.
Outcome: The proposed framework achieves 8.9% higher Scenario Goal Completion when applied to supervised-finetuned model with expert experience while requiring 26% fewer interaction steps and generating 59% fewer tokens.
SAGE : A Top-Down Bottom-Up Knowledge-Grounded User Simulator for Multi-turn Agent Evaluation (2026.findings-eacl)

Copied to clipboard

Challenge: Existing evaluation methods rely on static benchmarks or narrow task-specific datasets that fail to capture the open-ended nature of real-world interactions.
Approach: They propose a user Simulation framework for multi-turn AGent Evaluation that integrates top-down knowledge from business contexts and bottom-up knowledge from agent infrastructure.
Outcome: The proposed framework produces interactions that are more realistic and diverse while identifying up to 33% more agent errors.
SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback (2026.findings-eacl)

Copied to clipboard

Challenge: High-quality, complex question-answer pairs are pivotal for training and evaluating capable deep search agents.
Approach: They propose a pipeline that generates high-quality, difficulty-controlled deep search question-answer pairs for a given corpus and a target difficulty level.
Outcome: The proposed pipeline generates high-quality, difficulty-controlled deep search question-answer pairs for a given corpus and a target difficulty level.
SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation (2026.acl-long)

Copied to clipboard

Challenge: Recent approaches to generate tabular data are limited by their static dependences and lack of fidelity.
Approach: They propose a novel LLM-based generation framework that enforces sparse and dynamic dependency guidance.
Outcome: The proposed framework boosts F1 scores by 10% and reduces policy violations by one point.
Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated impressive capabilities across various tasks but are vulnerable to meticulously crafted jailbreak attacks.
Approach: They propose a training-free defense strategy to align LLMs’ strong safety discrimination performance with their relatively weaker safety generation ability.
Outcome: The proposed strategy achieves an average 99% success rate against numerous complex and covert jailbreak methods while maintaining helpfulness on general benchmarks.
Forward Knows Efficient Backward Path: Saliency-Guided Memory-Efficient Fine-tuning of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: a number of fine-tuning approaches are available to improve performance of large language models.
Approach: They propose a memory-efficient method to minimize memory associated with cached intermediate activations.
Outcome: The proposed method minimizes memory associated with cached intermediate activations while preserving accuracy.
SAGE: Synergistic Adaptive Gating of Experts for Hateful Video Detection (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for hateful video detection rely on multimodal feature fusion . existing methods rely only on blind feature mixing, which leads to feature dilution .
Approach: They propose a framework that shifts from blind feature mixing to decision-level arbitration . it instantiates disentangled experts to rigorously preserve modality-specific semantics .
Outcome: The proposed framework outperforms state-of-the-art methods on HateMM and MultiHateClip benchmarks.
Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been successful in Text-to-SQL tasks, but their deployment in real-world environments is hindered by latent reliability issues.
Approach: They propose a framework to autonomously uncover latent failure patterns in LLM-based Text-to-SQL generation.
Outcome: The proposed framework uncovers a substantial number of failure cases on state-of-the-art open-source LLMs.
SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods to train LLMs consume memory equivalent to twice the model size, resulting in a hybrid design that reverts to AdamW and negates the memory gains.
Approach: They propose a new, memory-efficient O(d) adaptive scale that replaces AdamW in a hybrid structure that combines a Lion-style update direction with a memory-saving adaptive scale.
Outcome: The proposed model outperforms existing methods on LLMs up to 1.3B parameters while significantly reducing optimizer state memory.
SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies on multimodal faithfulness have focused on perceptual hallucinations, raising concerns about the validity of reasoning traces.
Approach: They propose a diagnostic benchmark that enforces explicit visual comparison to assess faithfulness of reasoning traces.
Outcome: The proposed framework improves visual routing and aligns reasoning with perception.
Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data (2025.emnlp-main)

Copied to clipboard

Challenge: Existing literature suggests that RAG systems may face privacy issues when the retrieval process involves private data.
Approach: They propose a two-stage synthetic data generation paradigm that uses attributes to preserve contextual information from the original data.
Outcome: The proposed approach preserves key contextual information from the original data while reducing privacy risks.
Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have evolved from statistical sequence predictors to sophisticated autonomous agents capable of reasoning, planning, and sustaining multi-turn conversa-tions.
Approach: They propose a system that instantiates a "Sentient Agent" that simulates human-like emotional changes and inner thoughts to provide a more realistic evaluation of the model in multi-turn conversations.
Outcome: The proposed framework measures the agent's higher-order social cognition in multi-turn conversations.

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