This repo investigates LLMs' tendency to exhibit acquiescence bias in sequential QA interactions. Includes evaluation methods, datasets, benchmarks, and experiment code to assess and mitigate vulnerabilities in conversational consistency and robustness, offering a reproducible framework for future research.

Pytorch Implementation of "Sequential Dialogue Context Modeling for Spoken Language Understanding( https://arxiv.org/abs/1705.03455 )"

Entity extraction using BERT + CRF for single-tun / multi-turn setting in dialogues

[EMNLP 2025 main] C3 Benchmark: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations

collect the open dialog corpus and some useful data processing utils.

EMNLP 2019: Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots

A smart AI assistant for clinics using LangGraph, LangChain, and OpenAI GPT. It handles patient queries, schedules appointments, detects emergencies, and updates medical records through multi-turn, memory-aware conversations.

[NeurIPS 2025 Spotlight] InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback

MultiTurnResponseSelection

Multi-turn & Emotional Chatbot

A smart AI assistant for clinics using LangGraph, LangChain, and OpenAI GPT. It handles patient queries, schedules appointments, detects emergencies, and updates medical records through multi-turn, memory-aware conversations.

Tutor Agent is an AI-powered educational assistant that leverages a multi-agent along with multi turn architecture to provide specialized tutoring in mathematics and physics (with extensibility for more domains). It uses Google's Gemini API for LLM-powered reasoning, and routes student queries to the most appropriate specialist agent, which can use

PLD: Runtime Phase Model for Stable Multi-Turn LLM Systems

Conversation compression method for multi-turn RAG

A benchmark evolving framework and a benchmark for LLMs' multi-turn instruction following evaluation.