Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Same Answer, Different Future: Matched Predictions Do Not Imply Matched Belief Updating in Language Models
Weihan Li, Junhao Wu, Xinlei Chen +1
Language models can produce similar probabilistic predictions after observing outcomes, reading summaries, receiving instructions, or undergoing activation interventions. Whether t…
cs.LG2026
Same Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent?
Weihan Li, Xinlei Chen, Yuhan Song +2
Claims about what an internal direction in an LLM represents need evidential constraints beyond an observer's prior beliefs about the system. Decodability and successful activation…