Lightnews — Scholar-powered news

EunJeong Hwang

@ejhwang.bsky.social

250 followers 75 following 11 posts

PhD @ UBC. LLMs/NLP

Posts Media Videos Starter Packs

Pinned

EunJeong Hwang @ejhwang.bsky.social · 12d

Theory 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.🧵👇

1 2 4

EunJeong Hwang @ejhwang.bsky.social · 12d

Co-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!

EunJeong Hwang @ejhwang.bsky.social · 12d

Our 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.

1 2

EunJeong Hwang @ejhwang.bsky.social · 12d

We 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.

EunJeong Hwang @ejhwang.bsky.social · 12d

We 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).

EunJeong Hwang @ejhwang.bsky.social · 12d

ToMA adapts effectively to long conversations, sustaining strategic dialogue. When paired with diverse partners, it improves both its own goal completion and its partners’ success.

EunJeong Hwang @ejhwang.bsky.social · 12d

ToMA 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.

EunJeong Hwang @ejhwang.bsky.social · 12d

1 2 4

EunJeong Hwang @ejhwang.bsky.social · Nov 24

👋

EunJeong Hwang @ejhwang.bsky.social · Nov 23

Im also curious about this

Yoav Goldberg @yoavgo.bsky.social · Nov 23

let's talk about "agents" (in the LLM sense). there's a lot of buzz around "multi-agent" systems where agents collaborate but... i don't really get how it differs from a thinking of a single agent with multiple modes of operation. what are the benefits of modeling as multi-agent?

EunJeong Hwang @ejhwang.bsky.social · Nov 22

Also, 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!

EunJeong Hwang @ejhwang.bsky.social · Nov 22

We 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...

1 3