Reposted by EunJeong HwangNatalie Shapira @natalieshapira.bsky.social · 23/02/2026In this amazing multidisciplinary collaboration, we report our early experience with the @openclaw-x.bsky.social -> 14022
EunJeong Hwang @ejhwang.bsky.social · 03/10/2025Co-lead with @yuweiyin.bsky.social Huge thanks to @veredshwartz.bsky.social, Peter West, Giuseppe Carenini Paper: huggingface.co/papers/2509.... Code will be released soon! 000
EunJeong Hwang @ejhwang.bsky.social · 03/10/2025Our findings highlight that: 👉 Social reasoning in LLMs cannot be achieved through optimizing their performance on general reasoning benchmarks alone! 👉It requires explicit modeling of mental states to enable safe, fair, and effective interactions with humans. 120
EunJeong Hwang @ejhwang.bsky.social · 03/10/2025We also examine mental states (beliefs, desires, intentions, emotions, knowledge). 🔹 ToMA prioritizes intentions > emotions (other dimensions remain similar) 🔹 Uses +5.6% more 1st-order belief than bases, even when both are prompted equally for 0th/1st order states. 100
EunJeong Hwang @ejhwang.bsky.social · 03/10/2025We analyze 4 scenario types: cooperation, negotiation, persuasion, and conflict. ToMA outperforms the base under all settings. Its reasoning is more strategic (e.g., compromise, accommodation). Even in failures, ToMA shows more active engagement (e.g., failed persuasion). 100
EunJeong Hwang @ejhwang.bsky.social · 03/10/2025ToMA adapts effectively to long conversations, sustaining strategic dialogue. When paired with diverse partners, it improves both its own goal completion and its partners’ success. 100
EunJeong Hwang @ejhwang.bsky.social · 03/10/2025ToMA generates latent mental states and utterances optimized for social interaction goals using dialogue simulation signals. On Sotopia, it improves performance by +18.9% with Qwen2.5-3B and +6.9% with Qwen2.5-7B, while remaining competitive with a GPT-5 nano baseline. 100
EunJeong Hwang @ejhwang.bsky.social · 03/10/2025Theory of Mind can make LLMs better at dialogue: more strategic, goal-oriented, enabling long-horizon adaptation! In our new paper, we introduce ToMA, a dialogue lookahead training framework that enables the LLMs to generate mental states that are maximally useful for achieving dialogue goals.🧵👇 141
EunJeong Hwang @ejhwang.bsky.social · 22/11/2024Also, consider presenting a poster showcasing any ongoing projects or previously presented works from recent conferences. It will be a great chance to get feedback and promote your work! 010
EunJeong Hwang @ejhwang.bsky.social · 22/11/2024We are organizing an NLP workshop in Vancouver on Dec 10. Consider registering if you're here for NeurIPS - it's free and open to everyone who is interested in NLP! We have great members for invited talks and panel discussions. More details here: nlp.cs.ubc.ca/future-of-nl... 130
