Papers with Phi3

6 papers
Intrinsic Model Weaknesses: How Priming Attacks Unveil Vulnerabilities in Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Large language models (LLMs) have significant impact on various industries and societal functions due to advanced instruction-following capabilities.
Approach: They developed and tested novel attack strategies on popular LLMs to expose their vulnerabilities in generating harmful content.
Outcome: The proposed attacks achieved an ASR of 100% on open-source models, including Meta’s Llama-3.2, Google’s Gemma-2, Mistral’s Mistral-NeMo, Falcon’s Falcon-mamba, Apple’s DCLM, Microsoft’s Phi3, and Qwen’s Qwend2.5, among others.
I know you are different! Towards Persona Driven Knowledge-infused Dialogue Assistant (2026.eacl-long)

Copied to clipboard

Challenge: Task-Oriented Dialogue (TOD) systems often fall short in delivering personalized, context-rich responses, especially in low-resource, code-mixed, and multimodal settings like Hinglish.
Approach: They propose a Hinglish multimodal, multidomain, persona-based TOD dataset that captures user-agent interactions across text and visual modalities.
Outcome: The proposed framework outperforms standard and ablated models in Hinglish and Hinglanish.
Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) generate long one-sentence responses that are less effective because they overlook two crucial factors: intra-cluster similarity and inter-c cluster similarity.
Approach: They propose a method that generalizes semantic entropy and uses token probabilities to quantify uncertainty in large language models.
Outcome: The proposed method can be extended to white-box settings by incorporating token probabilities.
Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping (2025.findings-acl)

Copied to clipboard

Challenge: Knowledge distillation (KD) approaches focus on homogeneous architectures with identical tokenizers, constraining their applicability in cross-architecture scenarios.
Approach: They propose a framework that uses contextual information to enhance sequence alignment precision and dynamically improves vocabulary mapping.
Outcome: The proposed framework shows significant advantages over existing methods for model compression . it can be used across multiple model families and across multiple benchmarks .
Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation (2024.findings-emnlp)

Copied to clipboard

Challenge: Current LLMs are achieving better performance on various benchmarks, but their performance in practical applications does not always match their benchmark results.
Approach: They propose to detect and rewrite leaked benchmarks without altering their difficulties by using Inference-Time Decontamination (ITD) to mitigate performance inflation caused by memorizing leaked samples.
Outcome: The proposed method reduces inflated accuracy by 22.9% on GSM8K and 19.0% on MMLU.
Enhancing Goal-oriented Proactive Dialogue Systems via Consistency Reflection and Correction (2025.acl-long)

Copied to clipboard

Challenge: Unlike traditional dialogue systems, goal-oriented proactive dialogue systems focus on achieving specific objectives by actively guiding and anticipating user needs.
Approach: They propose a model-agnostic two-stage Consistency Reflection and Correction framework that allows the model to reflect on discrepancies between generated responses and dialogue contexts and suggest possible corrections.
Outcome: The proposed framework significantly improves the consistency between generated responses and dialogue contexts on three datasets.

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