One tiny word changes the conversation: how LLMs pick up on 'just'
StellaLisy · x · 2026-10-16
Using human-LLM comparisons, generation experiments, and mech interp methods, researchers show that a single word — "We're friends" vs "We're just friends" — measurably shifts how LLMs continue a conversation. Their experiments compare model probability sensitivity to sentences with and without the particle, and differences in generated follow-ups.
More from Research
- RExBench: best coding agent completes only 33% of autonomous research extensions — najoungkim · 2026-10-16
- Google's CLASHarness benchmarks multi-agent conflicts in computer use, finds frontier VLMs struggle — google · 2026-10-16
- Tsinghua team proves vanilla flow-matching sampling can't exceed constant-depth expressive power — SQZ · 2026-10-16
- APEX-Harm benchmark: script-based injection attacks easily compromise agents in shared workspaces — KAUST · 2026-10-16
- Residual-stream forecasts predict agent violations before they happen, USC study shows — USC · 2026-10-16
- KAUST's NoteBank adds sparse episodic memory to linear attention, boosting long-context for free — kaust-generative-ai · 2026-10-16