Shows
Daily Paper CastToo Good to be Bad: On the Failure of LLMs to Role-Play Villains
🤗 Upvotes: 34 | cs.CL, cs.AI
Authors:
Zihao Yi, Qingxuan Jiang, Ruotian Ma, Xingyu Chen, Qu Yang, Mengru Wang, Fanghua Ye, Ying Shen, Zhaopeng Tu, Xiaolong Li, Linus
Title:
Too Good to be Bad: On the Failure of LLMs to Role-Play Villains
Arxiv:
http://arxiv.org/abs/2511.04962v1
Abstract:
Large Language Models (LLMs) are increasingly tasked with creative generation, including the simulation of fictional characters. However, their ability to portray non-prosocial, antagonistic personas remains largely unexamined. We hypothesize that the safety alignment of modern LLMs creates a fundamental con...
2025-11-1125 minDaily Paper CastRLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
🤗 Upvotes: 27 | cs.CL, cs.AI, cs.CY
Authors:
Peisong Wang, Ruotian Ma, Bang Zhang, Xingyu Chen, Zhiwei He, Kang Luo, Qingsong Lv, Qingxuan Jiang, Zheng Xie, Shanyi Wang, Yuan Li, Fanghua Ye, Jian Li, Yifan Yang, Zhaopeng Tu, Xiaolong Li
Title:
RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
Arxiv:
http://arxiv.org/abs/2507.03112v1
Abstract:
Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional intelligence (EQ) still lags far behind their cognitive prowess. While reinforcement learning from verifiable rewards (RLVR) has...
2025-07-1021 minDaily Paper CastS$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
🤗 Upvotes: 15 | cs.CL, cs.LG
Authors:
Ruotian Ma, Peisong Wang, Cheng Liu, Xingyan Liu, Jiaqi Chen, Bang Zhang, Xin Zhou, Nan Du, Jia Li
Title:
S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
Arxiv:
http://arxiv.org/abs/2502.12853v1
Abstract:
Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs' deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains unclear how to improve the thinking abilities of less powerful base models. In this wor...
2025-02-2223 min
Electric CitiesS6 Episode 4: ULI 2021 Hines Student Competition: An Interview with the Winning Team from 3 Toronto UniversitiesEach year, the prestigious ULI Hines Student Competition attracts graduate student teams from all over North America to tackle complex urban design and development challenges.
This year’s competition was won by a team of 5 graduate students from 3 Toronto universities, the first time the annual competition has been won by a team outside the United States.
Jeremy sat down with the 5 graduate students and their 2 academic supervisors to learn more about this demanding competition, their fabulous submission, and what it took to capture the grand prize of $50,000 USD.
His 5 student guests were Frances Gr...
2021-05-0454 min