1 citations · 1 across the 9 of their papers we have counts for
9 papers
Dialogue Model Optimization via Agent Game and Adaptive Tree-based GRPO
Kun Peng, Conghui Tan, Yu Liu +7
Open-ended dialogue agents aim to deliver engaging, personalized interactions by adapting to users' traits, but existing methods face critical limitations: over-reliance on pre-col…
Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization
Jiecong Wang, Hao Peng, Chunyang Liu +2
Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems, but remains constrained by the computational cost and early token commitments in discrete r…
ReBeCA: Causality-Inspired Behavior Analysis for Understanding the Self-Reflection of Language Models
Tianqiang Yan, Lizhen Qu, Sihan Shang +6
Self-reflection is a basic self-improvement skill of language agents, yet it does not reliably improve their outputs, where the underlying behavioral mechanism remains opaque. We i…
Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures
Yi Hu, Jiaqi Gu, Ruxin Wang +6
Reinforcement learning (RL) has catalyzed the emergence of Large Reasoning Models (LRMs) that have pushed reasoning capabilities to new heights. While their performance has garnere…
MuVaC: A Variational Causal Framework for Multimodal Sarcasm Understanding in Dialogues
Diandian Guo, Fangfang Yuan, Cong Cao +5
The prevalence of sarcasm in multimodal dialogues on the social platforms presents a crucial yet challenging task for understanding the true intent behind online content. Comprehen…
Generalization of RLVR Using Causal Reasoning as a Testbed
Brian Lu, Hongyu Zhao, Shuo Sun +3
Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for post-training large language models (LLMs) on complex reasoning tasks. Yet, the condit…
Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code
Aniket Vashishtha, Qirun Dai, Hongyuan Mei +3
Counterfactual reasoning, a hallmark of intelligence, consists of three steps: inferring latent variables from observations (abduction), constructing alternatives (interventions),…
LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought
Zhuoxuan Jiang, Haoyuan Peng, Shanshan Feng +2
Self-correction is emerging as a promising approach to mitigate the issue of hallucination in Large Language Models (LLMs). To facilitate effective self-correction, recent research…
Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals
Yanai Elazar, Bhargavi Paranjape, Hao Peng +5
The inevitable appearance of spurious correlations in training datasets hurts the generalization of NLP models on unseen data. Previous work has found that datasets with paired inp…